Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- LICENSE.txt +7 -0
- README.md +460 -0
- chat_template.jinja +390 -0
- config.json +978 -0
- generation_config.json +14 -0
- merge_scale_info.txt +3 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- processor_config.json +75 -0
- tokenizer.json +3 -0
- tokenizer_config.json +96 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
By using this model, you agree:
|
| 2 |
+
|
| 3 |
+
Apache-2.0 (matching the Gemma 4 base). Constituent training datasets carry their own licenses (see the Athanorlite-DPO card on the nbeerbower/Gemma4-Gutenberg-31 model).
|
| 4 |
+
To accept full responsibility for all generated content
|
| 5 |
+
That you're at least 18+ years old
|
| 6 |
+
That the architects bear no responsibility for your corruption
|
| 7 |
+
This model is intended for personal usage only. Using this model for profit and/or for commerical use is not allowed to the extent legally permitted by the original license.
|
README.md
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- nbeerbower/Gemma4-Gutenberg-31B
|
| 4 |
+
base_model_relation: finetune
|
| 5 |
+
tags:
|
| 6 |
+
- gemma-4
|
| 7 |
+
- roleplay
|
| 8 |
+
- conversational
|
| 9 |
+
- instruct
|
| 10 |
+
- apache-2.0
|
| 11 |
+
- nsfw
|
| 12 |
+
- adult-content
|
| 13 |
+
- unaligned
|
| 14 |
+
- mature
|
| 15 |
+
- explicit
|
| 16 |
+
- erp
|
| 17 |
+
license: apache-2.0
|
| 18 |
+
---
|
| 19 |
+
<style>
|
| 20 |
+
@import url('https://fonts.googleapis.com/css2?family=Cinzel:wght@400;700;900&family=Raleway:wght@300;400;600;700&family=JetBrains+Mono:wght@400;700&display=swap');
|
| 21 |
+
|
| 22 |
+
/* Base Reset & Layout */
|
| 23 |
+
.mc-wrap{background:#08060b;color:#e0dce4;font-family:'Raleway',sans-serif;max-width:920px;margin:0 auto;padding:24px;border-radius:16px;box-sizing:border-box;position:relative;overflow:hidden;
|
| 24 |
+
background-image:
|
| 25 |
+
radial-gradient(ellipse at 20% 50%, rgba(120,20,50,0.08) 0%, transparent 50%),
|
| 26 |
+
radial-gradient(ellipse at 80% 20%, rgba(80,10,60,0.06) 0%, transparent 50%),
|
| 27 |
+
radial-gradient(ellipse at 50% 80%, rgba(140,30,70,0.05) 0%, transparent 50%)}
|
| 28 |
+
.mc-wrap::before{content:'';position:absolute;top:0;left:0;right:0;bottom:0;background:url("data:image/svg+xml,%3Csvg width='60' height='60' viewBox='0 0 60 60' xmlns='http://www.w3.org/2000/svg'%3E%3Cg fill='none' fill-rule='evenodd'%3E%3Cg fill='%23ff2a6d' fill-opacity='0.03'%3E%3Cpath d='M36 34v-4h-2v4h-4v2h4v4h2v-4h4v-2h-4zm0-30V0h-2v4h-4v2h4v4h2V6h4V4h-4zM6 34v-4H4v4H0v2h4v4h2v-4h4v-2H6zM6 4V0H4v4H0v2h4v4h2V6h4V4H6z'/%3E%3C/g%3E%3C/g%3E%3C/svg%3E") repeat;pointer-events:none;z-index:0;opacity:0.5}
|
| 29 |
+
.mc-wrap *{box-sizing:border-box;position:relative;z-index:1}
|
| 30 |
+
.mc-wrap h1,.mc-wrap h2,.mc-wrap h3,.mc-wrap h4{color:#ffffff;border:none;font-family:'Cinzel',serif}
|
| 31 |
+
.mc-wrap p{color:#c8c0cc;font-family:'Raleway',sans-serif;line-height:1.7}
|
| 32 |
+
.mc-wrap strong{color:#ff2a6d;font-weight:600}
|
| 33 |
+
.mc-wrap a{color:#ff6b9d;text-decoration:none;transition:all 0.3s;border-bottom:1px solid transparent}
|
| 34 |
+
.mc-wrap a:hover{color:#ff2a6d;border-bottom-color:#ff2a6d}
|
| 35 |
+
.mc-wrap ul{list-style:none;padding-left:0;margin:0}
|
| 36 |
+
.mc-wrap li{color:#c8c0cc;margin-bottom:10px;padding-left:0;line-height:1.7}
|
| 37 |
+
|
| 38 |
+
/* Code Blocks */
|
| 39 |
+
.mc-wrap code{background:rgba(255,42,109,0.08);color:#ff6b9d;padding:3px 10px;border-radius:4px;font-family:'JetBrains Mono',monospace;font-size:.85em;border:1px solid rgba(255,42,109,.2)}
|
| 40 |
+
|
| 41 |
+
/* Ornamental Dividers */
|
| 42 |
+
.mc-ornament{text-align:center;margin:28px 0;position:relative;z-index:1}
|
| 43 |
+
.mc-ornament::before{content:'';position:absolute;top:50%;left:10%;right:10%;height:1px;background:linear-gradient(90deg,transparent,rgba(255,42,109,0.3),rgba(200,150,180,0.4),rgba(255,42,109,0.3),transparent)}
|
| 44 |
+
.mc-ornament span{background:#08060b;padding:0 20px;color:#ff2a6d;font-size:1.2em;position:relative;z-index:2}
|
| 45 |
+
|
| 46 |
+
/* Header Section */
|
| 47 |
+
.mc-hdr{text-align:center;padding:50px 40px;background:linear-gradient(180deg,#0d0a10 0%,#12090f 50%,#0d0a10 100%);border:1px solid rgba(255,42,109,.25);border-radius:24px;margin-bottom:24px;position:relative;overflow:hidden;box-shadow:0 0 40px rgba(255,42,109,0.08),inset 0 0 60px rgba(0,0,0,0.3)}
|
| 48 |
+
.mc-hdr::before{content:'';position:absolute;top:0;left:0;right:0;height:3px;background:linear-gradient(90deg,transparent,#ff2a6d,#d90429,#c7728a,#d90429,#ff2a6d,transparent);animation:shimmer 4s ease infinite}
|
| 49 |
+
.mc-hdr::after{content:'';position:absolute;bottom:0;left:0;right:0;height:3px;background:linear-gradient(90deg,transparent,#8d0801,#d90429,#ff2a6d,#d90429,#8d0801,transparent);animation:shimmer 4s ease infinite reverse}
|
| 50 |
+
.mc-name{font-family:'Cinzel',serif;font-size:2.8em;font-weight:900;margin:0;letter-spacing:.08em;background:linear-gradient(135deg,#ff2a6d 0%,#ff6b9d 25%,#c7728a 50%,#ff2a6d 75%,#d90429 100%);-webkit-background-clip:text;-webkit-text-fill-color:transparent;background-clip:text;line-height:1.3;text-shadow:0 0 30px rgba(255,42,109,0.4);background-size:200% 200%;animation:text-shimmer 6s ease infinite}
|
| 51 |
+
.mc-badge{display:inline-flex;align-items:center;gap:8px;background:linear-gradient(135deg,rgba(255,42,109,.12),rgba(140,8,1,.15));border:1px solid rgba(255,42,109,.45);padding:10px 24px;border-radius:100px;font-family:'JetBrains Mono',monospace;font-size:.85em;font-weight:700;color:#ff2a6d;margin-top:22px;box-shadow:0 0 20px rgba(255,42,109,0.15);animation:pulse-badge 3s infinite;letter-spacing:.05em}
|
| 52 |
+
.mc-sub{color:#9a8fa0;font-size:1.15em;margin-top:18px;font-weight:300;font-style:italic;font-family:'Raleway',sans-serif;letter-spacing:.04em}
|
| 53 |
+
|
| 54 |
+
/* Warnings & Alerts */
|
| 55 |
+
.mc-warn{padding:18px 28px;border-radius:12px;margin:24px 0;font-weight:600;font-size:.88em;line-height:1.7;background:linear-gradient(135deg,rgba(217,4,41,.08),rgba(140,8,1,.06));border:1px solid rgba(217,4,41,.35);color:#ff4d6d;text-align:center;box-shadow:0 0 20px rgba(217,4,41,0.06);position:relative;overflow:hidden}
|
| 56 |
+
.mc-warn::before{content:'';position:absolute;top:0;left:0;right:0;height:2px;background:linear-gradient(90deg,transparent,#d90429,#ff4d6d,#d90429,transparent)}
|
| 57 |
+
|
| 58 |
+
/* Sections */
|
| 59 |
+
.mc-sec{margin:20px 0;padding:28px 32px;background:linear-gradient(180deg,#0c0a0f,#0a0810);border:1px solid rgba(255,42,109,.15);border-radius:16px;position:relative;overflow:hidden;transition:all 0.4s ease}
|
| 60 |
+
.mc-sec:hover{border-color:rgba(255,42,109,.4);box-shadow:0 0 30px rgba(255,42,109,0.06)}
|
| 61 |
+
.mc-sec::before{content:'';position:absolute;top:0;left:0;width:3px;height:100%;background:linear-gradient(180deg,#ff2a6d,#d90429,#c7728a,#8d0801);opacity:.9}
|
| 62 |
+
.mc-sec::after{content:'';position:absolute;top:0;right:0;bottom:0;width:60px;background:linear-gradient(90deg,transparent,rgba(255,42,109,0.02));pointer-events:none}
|
| 63 |
+
.mc-sec-title{font-family:'Cinzel',serif;font-size:1.4em;font-weight:700;margin:0 0 18px 0;color:#ffffff;display:flex;align-items:center;gap:12px;letter-spacing:.04em}
|
| 64 |
+
|
| 65 |
+
/* Grids & Cards */
|
| 66 |
+
.mc-grid{display:grid;grid-template-columns:1fr 1fr;gap:16px;margin-top:18px}
|
| 67 |
+
.mc-card{background:linear-gradient(145deg,#0f0c14,#0c0a10);padding:22px;border-radius:14px;border:1px solid rgba(255,42,109,.12);transition:all 0.4s ease;position:relative;overflow:hidden}
|
| 68 |
+
.mc-card::before{content:'';position:absolute;top:0;left:0;right:0;height:2px;background:linear-gradient(90deg,transparent,rgba(255,42,109,0.3),transparent);opacity:0;transition:opacity 0.4s}
|
| 69 |
+
.mc-card:hover{border-color:rgba(255,42,109,.4);box-shadow:0 0 25px rgba(255,42,109,0.08);transform:translateY(-3px)}
|
| 70 |
+
.mc-card:hover::before{opacity:1}
|
| 71 |
+
.mc-card h4{margin:0 0 12px 0;color:#ff2a6d;font-family:'Cinzel',serif;font-weight:700;font-size:1em;letter-spacing:.03em}
|
| 72 |
+
.mc-card p{color:#b8b0c0;font-size:.88em;margin:0;line-height:1.7}
|
| 73 |
+
.mc-val{font-family:'Cinzel',serif;font-size:2.6em;font-weight:900;background:linear-gradient(135deg,#ff2a6d,#d90429,#c7728a);-webkit-background-clip:text;-webkit-text-fill-color:transparent;background-clip:text;margin:10px 0;line-height:1}
|
| 74 |
+
.mc-lbl{color:#8a7f90;font-size:.82em;line-height:1.6;margin:0}
|
| 75 |
+
|
| 76 |
+
/* Tables */
|
| 77 |
+
.mc-tbl{width:100%;border-collapse:separate;border-spacing:0;margin-top:18px;font-family:'Raleway',sans-serif;border-radius:14px;border:1px solid rgba(255,42,109,.15);overflow:hidden}
|
| 78 |
+
.mc-tbl th{background:linear-gradient(135deg,rgba(255,42,109,.1),rgba(140,8,1,.08));color:#ff2a6d;padding:14px 22px;text-align:left;font-weight:700;font-size:.72em;text-transform:uppercase;letter-spacing:.12em;border-bottom:1px solid rgba(255,42,109,.2);font-family:'Cinzel',serif}
|
| 79 |
+
.mc-tbl td{padding:14px 22px;border-bottom:1px solid rgba(255,42,109,.08);color:#c8c0cc;font-size:.86em;background:#0c0a10;font-family:'Raleway',sans-serif}
|
| 80 |
+
.mc-tbl tr:last-child td{border-bottom:none}
|
| 81 |
+
.mc-tbl tr:hover td{background:rgba(255,42,109,0.03)}
|
| 82 |
+
.mc-tbl td strong{color:#d90429}
|
| 83 |
+
|
| 84 |
+
/* Buttons & Links */
|
| 85 |
+
.mc-qlinks{display:grid;grid-template-columns:repeat(auto-fit,minmax(220px,1fr));gap:16px;margin:18px 0}
|
| 86 |
+
.mc-btn{display:inline-flex;align-items:center;justify-content:center;background:linear-gradient(135deg,#ff2a6d,#d90429);color:#0a0a0a;padding:14px 28px;border-radius:10px;text-decoration:none;border:none;margin:14px 0 0 0;font-weight:700;font-size:.88em;letter-spacing:.06em;text-transform:uppercase;font-family:'Cinzel',serif;box-shadow:0 4px 20px rgba(255,42,109,.3);transition:all 0.4s ease;position:relative;overflow:hidden}
|
| 87 |
+
.mc-btn::before{content:'';position:absolute;top:0;left:-100%;width:100%;height:100%;background:linear-gradient(90deg,transparent,rgba(255,255,255,0.2),transparent);transition:0.6s}
|
| 88 |
+
.mc-btn:hover::before{left:100%}
|
| 89 |
+
.mc-btn:hover{box-shadow:0 0 35px rgba(255,42,109,0.5);transform:translateY(-3px);filter:brightness(1.1)}
|
| 90 |
+
.mc-ava{width:48px;height:48px;border-radius:50%;margin-right:16px;object-fit:cover;border:2px solid rgba(255,42,109,.6);box-shadow:0 0 15px rgba(255,42,109,0.2);transition:all 0.3s}
|
| 91 |
+
.mc-ava:hover{border-color:#ff2a6d;box-shadow:0 0 25px rgba(255,42,109,0.4)}
|
| 92 |
+
.mc-disclaimer{border-left:3px solid #c7728a;padding:16px 24px;background:linear-gradient(135deg,rgba(200,114,138,.06),rgba(255,153,170,.04));border-radius:0 14px 14px 0;color:#ddb8c8;font-size:.88em;margin:18px 0;line-height:1.7}
|
| 93 |
+
|
| 94 |
+
/* FLASHY TAGS & KINKS SECTION */
|
| 95 |
+
.mc-tag-container{display:flex;flex-wrap:wrap;gap:10px;margin:22px 0;justify-content:center}
|
| 96 |
+
.mc-tag{display:inline-flex;align-items:center;padding:8px 18px;border-radius:100px;font-size:.75em;font-weight:700;letter-spacing:.1em;text-transform:uppercase;font-family:'JetBrains Mono',monospace;border:1px solid;transition:all 0.4s ease;position:relative;overflow:hidden;backdrop-filter:blur(4px)}
|
| 97 |
+
.mc-tag::before{content:'';position:absolute;top:0;left:0;width:100%;height:100%;background:linear-gradient(45deg,transparent,rgba(255,255,255,0.12),transparent);transform:translateX(-100%);transition:0.6s}
|
| 98 |
+
.mc-tag:hover::before{transform:translateX(100%)}
|
| 99 |
+
.mc-tag:hover{transform:scale(1.08);box-shadow:0 0 20px currentColor}
|
| 100 |
+
|
| 101 |
+
.t1{background:rgba(255,42,109,.12);color:#ff2a6d;border-color:rgba(255,42,109,.5);box-shadow:0 0 12px rgba(255,42,109,0.15)}
|
| 102 |
+
.t2{background:rgba(217,4,41,.12);color:#d90429;border-color:rgba(217,4,41,.5);box-shadow:0 0 12px rgba(217,4,41,0.15)}
|
| 103 |
+
.t3{background:rgba(141,8,1,.12);color:#c75050;border-color:rgba(141,8,1,.5);box-shadow:0 0 12px rgba(141,8,1,0.15)}
|
| 104 |
+
.t4{background:rgba(200,114,138,.12);color:#c7728a;border-color:rgba(200,114,138,.5);box-shadow:0 0 12px rgba(200,114,138,0.15)}
|
| 105 |
+
.t-nsfw{background:rgba(255,0,85,.15);color:#ff0055;border-color:rgba(255,0,85,.6);box-shadow:0 0 18px rgba(255,0,85,0.3);animation:pulse-red 2.5s infinite}
|
| 106 |
+
|
| 107 |
+
/* Special Kink Highlight Box */
|
| 108 |
+
.kink-highlight{background:linear-gradient(145deg, #12081a, #0a0610, #0f0a14);border:1px solid rgba(255,42,109,.3);border-radius:20px;padding:30px;margin:24px 0;position:relative;overflow:hidden}
|
| 109 |
+
.kink-highlight::before{content:'';position:absolute;top:-1px;left:-1px;right:-1px;bottom:-1px;border-radius:20px;background:linear-gradient(135deg,rgba(255,42,109,0.2),transparent 40%,transparent 60%,rgba(200,114,138,0.15));z-index:0;pointer-events:none}
|
| 110 |
+
.kink-highlight::after{content:'';position:absolute;top:-50%;right:-30%;width:80%;height:100%;background:radial-gradient(circle,rgba(255,42,109,0.08) 0%,transparent 70%);pointer-events:none;z-index:0}
|
| 111 |
+
.kink-stat-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(150px,1fr));gap:16px;margin-top:22px}
|
| 112 |
+
.kink-stat{background:linear-gradient(145deg,rgba(255,42,109,0.04),rgba(200,114,138,0.02));border:1px solid rgba(255,42,109,.15);padding:20px;border-radius:14px;text-align:center;transition:all 0.4s ease;position:relative;overflow:hidden}
|
| 113 |
+
.kink-stat::before{content:'';position:absolute;top:0;left:0;right:0;height:2px;background:linear-gradient(90deg,transparent,rgba(255,42,109,0.4),transparent);opacity:0;transition:opacity 0.4s}
|
| 114 |
+
.kink-stat:hover{background:linear-gradient(145deg,rgba(255,42,109,0.08),rgba(200,114,138,0.04));border-color:rgba(255,42,109,.4);box-shadow:0 0 25px rgba(255,42,109,0.1);transform:translateY(-3px)}
|
| 115 |
+
.kink-stat:hover::before{opacity:1}
|
| 116 |
+
.kink-stat-val{font-family:'Cinzel',serif;font-size:1.8em;font-weight:900;color:#ff2a6d;display:block;margin-bottom:6px;text-shadow:0 0 20px rgba(255,42,109,0.3)}
|
| 117 |
+
.kink-stat-label{font-size:0.72em;color:#8a7f90;text-transform:uppercase;letter-spacing:.12em;font-family:'JetBrains Mono',monospace}
|
| 118 |
+
|
| 119 |
+
/* Video */
|
| 120 |
+
.mc-video-wrap{position:relative;margin:24px 0;border-radius:18px;overflow:hidden;border:2px solid rgba(255,42,109,.4);box-shadow:0 0 40px rgba(255,42,109,0.12)}
|
| 121 |
+
.mc-video-badge{position:absolute;top:12px;right:12px;background:linear-gradient(135deg,#ff2a6d,#d90429);color:#0a0a0a;font-family:'Cinzel',serif;font-weight:900;padding:6px 16px;font-size:.72em;border-radius:6px;z-index:2;border:1px solid rgba(255,42,109,.5);box-shadow:0 0 15px rgba(0,0,0,0.6);letter-spacing:.08em;text-transform:uppercase}
|
| 122 |
+
|
| 123 |
+
/* Details/Summary */
|
| 124 |
+
details summary{cursor:pointer;font-family:'Cinzel',serif;font-size:1.3em;font-weight:700;color:#ffffff;padding:22px 32px;background:linear-gradient(135deg,#110d16,#0c0a10);border:1px solid rgba(255,42,109,.15);border-radius:16px;position:relative;list-style:none;display:flex;align-items:center;gap:12px;transition:all 0.4s ease;letter-spacing:.03em}
|
| 125 |
+
details summary:hover{background:linear-gradient(135deg,#16101c,#0e0b14);border-color:rgba(255,42,109,.35);box-shadow:0 0 25px rgba(255,42,109,0.06)}
|
| 126 |
+
details summary::-webkit-details-marker{display:none}
|
| 127 |
+
details summary::before{content:'✦';font-size:.7em;transition:all .3s;color:#ff2a6d;margin-right:4px}
|
| 128 |
+
details[open] summary::before{content:'✦';transform:rotate(180deg);filter:drop-shadow(0 0 6px rgba(255,42,109,0.6))}
|
| 129 |
+
details summary::after{content:'';position:absolute;top:0;left:0;width:3px;height:100%;background:linear-gradient(180deg,#ff2a6d,#d90429,#c7728a);opacity:.8;border-radius:16px 0 0 16px}
|
| 130 |
+
details .mc-sec{margin-top:0;border-top-left-radius:0;border-top-right-radius:0;border-top:none}
|
| 131 |
+
|
| 132 |
+
/* Sampler & Config */
|
| 133 |
+
.sampler-grid{display:grid;grid-template-columns:1fr 1fr;gap:12px;margin-top:16px}
|
| 134 |
+
.param-box{background:linear-gradient(145deg,rgba(255,42,109,0.04),rgba(200,114,138,0.02));border:1px solid rgba(255,42,109,.15);padding:16px;border-radius:10px;text-align:center;transition:all 0.3s ease;position:relative;overflow:hidden}
|
| 135 |
+
.param-box::before{content:'';position:absolute;top:0;left:0;right:0;height:2px;background:linear-gradient(90deg,transparent,rgba(255,42,109,0.3),transparent);opacity:0;transition:opacity 0.3s}
|
| 136 |
+
.param-box:hover{background:linear-gradient(145deg,rgba(255,42,109,0.1),rgba(200,114,138,0.05));border-color:rgba(255,42,109,.4);box-shadow:0 0 20px rgba(255,42,109,0.12)}
|
| 137 |
+
.param-box:hover::before{opacity:1}
|
| 138 |
+
.param-val{font-family:'Cinzel',serif;font-size:1.6em;font-weight:900;color:#ff2a6d;display:block;margin-bottom:4px;text-shadow:0 0 15px rgba(255,42,109,0.3)}
|
| 139 |
+
.param-label{font-size:0.68em;color:#8a7f90;text-transform:uppercase;letter-spacing:.1em;font-family:'JetBrains Mono',monospace}
|
| 140 |
+
.quant-list{list-style:none;padding:0;margin:16px 0}
|
| 141 |
+
.quant-item{display:flex;justify-content:space-between;padding:10px 0;border-bottom:1px solid rgba(255,42,109,.1);font-size:.85em;color:#c8c0cc;transition:all 0.2s}
|
| 142 |
+
.quant-item:hover{padding-left:8px;border-bottom-color:rgba(255,42,109,.25)}
|
| 143 |
+
.quant-item:last-child{border-bottom:none}
|
| 144 |
+
.quant-item span:first-child{font-family:'JetBrains Mono',monospace;color:#d90429;font-weight:700}
|
| 145 |
+
.mc-btn-glow{box-shadow:0 0 20px rgba(255,42,109,0.3);transition:all 0.4s ease;width:100%}
|
| 146 |
+
.mc-btn-glow:hover{box-shadow:0 0 40px rgba(255,42,109,0.5);transform:translateY(-3px)}
|
| 147 |
+
.download-icon{margin-right:10px}
|
| 148 |
+
|
| 149 |
+
/* Art Corner Decorations */
|
| 150 |
+
.mc-corner-decor{position:absolute;width:30px;height:30px;opacity:.4;pointer-events:none}
|
| 151 |
+
.mc-corner-decor.tl{top:8px;left:8px;border-top:2px solid #ff2a6d;border-left:2px solid #ff2a6d}
|
| 152 |
+
.mc-corner-decor.tr{top:8px;right:8px;border-top:2px solid #ff2a6d;border-right:2px solid #ff2a6d}
|
| 153 |
+
.mc-corner-decor.bl{bottom:8px;left:8px;border-bottom:2px solid #ff2a6d;border-left:2px solid #ff2a6d}
|
| 154 |
+
.mc-corner-decor.br{bottom:8px;right:8px;border-bottom:2px solid #ff2a6d;border-right:2px solid #ff2a6d}
|
| 155 |
+
|
| 156 |
+
/* Notice Box */
|
| 157 |
+
.mc-notice{padding:22px 28px;border-radius:14px;margin:24px 0;font-size:.92em;line-height:1.7;background:linear-gradient(135deg,rgba(255,180,50,.06),rgba(200,150,50,.04));border:1px solid rgba(255,180,50,.35);color:#e8d4a0;text-align:center;box-shadow:0 0 20px rgba(255,180,50,0.06);position:relative;overflow:hidden}
|
| 158 |
+
.mc-notice::before{content:'';position:absolute;top:0;left:0;right:0;height:2px;background:linear-gradient(90deg,transparent,#ffb432,#ffd700,#ffb432,transparent)}
|
| 159 |
+
.mc-notice strong{color:#ffd700;font-weight:700}
|
| 160 |
+
.mc-notice code{background:rgba(255,180,50,0.12);color:#ffd700;border-color:rgba(255,180,50,.25)}
|
| 161 |
+
|
| 162 |
+
/* Animations */
|
| 163 |
+
@keyframes shimmer{0%{background-position:-200% 0}100%{background-position:200% 0}}
|
| 164 |
+
@keyframes text-shimmer{0%{background-position:0% 50%}50%{background-position:100% 50%}100%{background-position:0% 50%}}
|
| 165 |
+
@keyframes pulse-badge{0%{box-shadow:0 0 0 0 rgba(255,42,109,0.4)}70%{box-shadow:0 0 0 12px rgba(255,42,109,0)}100%{box-shadow:0 0 0 0 rgba(255,42,109,0)}}
|
| 166 |
+
@keyframes pulse-red{0%{box-shadow:0 0 0 0 rgba(255,0,85,0.4)}70%{box-shadow:0 0 0 12px rgba(255,0,85,0)}100%{box-shadow:0 0 0 0 rgba(255,0,85,0)}}
|
| 167 |
+
@keyframes float{0%{transform:translateY(0)}50%{transform:translateY(-5px)}100%{transform:translateY(0)}}
|
| 168 |
+
|
| 169 |
+
/* Responsive */
|
| 170 |
+
@media(max-width:640px){.mc-wrap{padding:12px}.mc-name{font-size:1.8em}.mc-grid{grid-template-columns:1fr}.mc-qlinks{grid-template-columns:1fr}.kink-stat-grid{grid-template-columns:1fr 1fr}.mc-hdr{padding:30px 20px}}
|
| 171 |
+
</style>
|
| 172 |
+
|
| 173 |
+
<div class="mc-wrap">
|
| 174 |
+
|
| 175 |
+
<div class="mc-hdr">
|
| 176 |
+
<div class="mc-corner-decor tl"></div>
|
| 177 |
+
<div class="mc-corner-decor tr"></div>
|
| 178 |
+
<div class="mc-corner-decor bl"></div>
|
| 179 |
+
<div class="mc-corner-decor br"></div>
|
| 180 |
+
<h1 class="mc-name">Dark Scarlett 31B</h1>
|
| 181 |
+
<div class="mc-badge">⚡ v2.0</div>
|
| 182 |
+
<p class="mc-sub">Passion ignited. Boundaries dissolved.</p>
|
| 183 |
+
<div style="background:linear-gradient(135deg,rgba(255,42,109,0.06),rgba(200,114,138,0.04));border:1px solid rgba(255,42,109,.2);padding:14px;border-radius:10px;margin-top:20px;font-size:.85em;color:#c7728a">
|
| 184 |
+
<strong>Thinking did not survive</strong> </div>
|
| 185 |
+
</div>
|
| 186 |
+
|
| 187 |
+
<div class="mc-ornament"><span>✦</span></div>
|
| 188 |
+
|
| 189 |
+
<!-- NOTICE: Same as v1.0 but on Gemma4-Gutenberg-31B -->
|
| 190 |
+
<div class="mc-notice">
|
| 191 |
+
<div class="mc-corner-decor tl"></div>
|
| 192 |
+
<div class="mc-corner-decor tr"></div>
|
| 193 |
+
<div class="mc-corner-decor bl"></div>
|
| 194 |
+
<div class="mc-corner-decor br"></div>
|
| 195 |
+
🔔 <strong>Version Notice:</strong> This model is the <strong>same training data and configuration as v1.0</strong>, now applied to the <strong>Gemma4-Gutenberg-31B</strong> base model. If you liked Dark Scarlett v1.0, this offers the same experience on an improved literary base.
|
| 196 |
+
</div>
|
| 197 |
+
|
| 198 |
+
<!-- FLASHY TAG CLOUD -->
|
| 199 |
+
<div class="mc-tag-container">
|
| 200 |
+
<span class="mc-tag t-nsfw">🔞 NSFW</span>
|
| 201 |
+
<span class="mc-tag t1">ERP</span>
|
| 202 |
+
<span class="mc-tag t2">Uncensored</span>
|
| 203 |
+
<span class="mc-tag t1">Roleplay</span>
|
| 204 |
+
<span class="mc-tag t3">Gemma-4</span>
|
| 205 |
+
<span class="mc-tag t4">Adult</span>
|
| 206 |
+
<span class="mc-tag t2">Unaligned</span>
|
| 207 |
+
</div>
|
| 208 |
+
|
| 209 |
+
<div class="mc-warn">
|
| 210 |
+
✦ Content Advisory: Mature Themes / Adult Interactions — Intended for mature audiences only. ✦
|
| 211 |
+
</div>
|
| 212 |
+
|
| 213 |
+
<!-- KINK HIGHLIGHT SECTION -->
|
| 214 |
+
<div class="kink-highlight">
|
| 215 |
+
<div class="mc-corner-decor tl"></div>
|
| 216 |
+
<div class="mc-corner-decor tr"></div>
|
| 217 |
+
<div class="mc-corner-decor bl"></div>
|
| 218 |
+
<div class="mc-corner-decor br"></div>
|
| 219 |
+
<h3 style="margin:0 0 12px 0;color:#ff2a6d;font-family:'Cinzel',serif;text-align:center;text-transform:uppercase;letter-spacing:.14em;font-size:1.1em">✦ Core Capabilities ✦</h3>
|
| 220 |
+
<p style="text-align:center;color:#8a7f90;font-size:.88em;margin:0;font-family:'Raleway',sans-serif">Optimized for immersive adult narrative experiences</p>
|
| 221 |
+
<div class="kink-stat-grid">
|
| 222 |
+
<div class="kink-stat">
|
| 223 |
+
<span class="kink-stat-val">6000+</span>
|
| 224 |
+
<span class="kink-stat-label">Kink Prompts (In Generator)</span>
|
| 225 |
+
</div>
|
| 226 |
+
<div class="kink-stat">
|
| 227 |
+
<span class="kink-stat-val">100%</span>
|
| 228 |
+
<span class="kink-stat-label">Uncensored</span>
|
| 229 |
+
</div>
|
| 230 |
+
<div class="kink-stat">
|
| 231 |
+
<span class="kink-stat-val">M→F</span>
|
| 232 |
+
<span class="kink-stat-label">Perspective</span>
|
| 233 |
+
</div>
|
| 234 |
+
</div>
|
| 235 |
+
</div>
|
| 236 |
+
|
| 237 |
+
<div class="mc-ornament"><span>⟡</span></div>
|
| 238 |
+
|
| 239 |
+
<div class="mc-video-wrap">
|
| 240 |
+
<span class="mc-video-badge">Gemma 4 Based</span>
|
| 241 |
+
<video autoplay loop muted playsinline controls style="width:100%;display:block;border-radius:16px">
|
| 242 |
+
<source src="https://huggingface.co/spaces/ReadyArt/README/resolve/main/Dark-Scarlett.mp4" type="video/mp4">
|
| 243 |
+
</video>
|
| 244 |
+
</div>
|
| 245 |
+
|
| 246 |
+
<div class="mc-ornament"><span>✦</span></div>
|
| 247 |
+
|
| 248 |
+
<details>
|
| 249 |
+
<summary>🌹 What Is Dark Scarlett?</summary>
|
| 250 |
+
<div class="mc-sec">
|
| 251 |
+
<p>Inspired by the <strong>spirit of Melody1437</strong>, though trained on a distinct dataset, <strong>Dark Scarlett-31B</strong> refines the core architecture with specialized scenario prompts to enhance depth and responsiveness. This model focuses on delivering a cohesive narrative experience with a distinct perspective.</p>
|
| 252 |
+
<div style="display:flex;align-items:center;justify-content:center;gap:20px;margin:24px 0;flex-wrap:wrap">
|
| 253 |
+
<div style="text-align:center;padding:22px 34px;background:linear-gradient(145deg,#0f0c14,#0c0a10);border-radius:14px;border:1px solid rgba(255,42,109,.15);min-width:150px">
|
| 254 |
+
<div style="font-family:'JetBrains Mono',monospace;font-size:.68em;text-transform:uppercase;letter-spacing:.14em;color:#8a7f90;margin-bottom:10px">Core Inspiration</div>
|
| 255 |
+
<div style="font-family:'Cinzel',serif;font-size:1.2em;font-weight:700;color:#ff2a6d">Melody1437 Spirit</div>
|
| 256 |
+
<div style="font-family:'JetBrains Mono',monospace;font-size:.65em;color:#d90429;margin-top:6px">Distinct Dataset</div>
|
| 257 |
+
</div>
|
| 258 |
+
<div style="font-size:1.8em;color:#d90429;text-shadow:0 0 15px rgba(217,4,41,0.4)">⟡</div>
|
| 259 |
+
<div style="text-align:center;padding:22px 34px;background:linear-gradient(145deg,rgba(255,42,109,.06),rgba(200,114,138,.04));border-radius:14px;border:1px solid rgba(255,42,109,.3);min-width:150px;box-shadow:0 0 25px rgba(255,42,109,.08)">
|
| 260 |
+
<div style="font-family:'JetBrains Mono',monospace;font-size:.68em;text-transform:uppercase;letter-spacing:.14em;color:#ff2a6d;margin-bottom:10px">Result</div>
|
| 261 |
+
<div style="font-family:'Cinzel',serif;font-size:1.4em;font-weight:900;background:linear-gradient(135deg,#ff2a6d,#d90429,#c7728a);-webkit-background-clip:text;-webkit-text-fill-color:transparent;background-clip:text">Dark Scarlett</div>
|
| 262 |
+
</div>
|
| 263 |
+
</div>
|
| 264 |
+
<div class="mc-warn" style="background:linear-gradient(135deg,rgba(200,114,138,.06),rgba(255,153,170,.04));border-color:rgba(200,114,138,.3);color:#ddb8c8">
|
| 265 |
+
⚠️ <strong>Perspective Note:</strong> Training data strictly follows a Male (User) → Female (AI) perspective for consistent roleplay dynamics.
|
| 266 |
+
</div>
|
| 267 |
+
<ul>
|
| 268 |
+
<li>🧠 <strong>Core Heritage:</strong> Captures the spirit of Melody1437 with diversified scenario prompts</li>
|
| 269 |
+
<li>🎭 <strong>Group Chat Support:</strong> Includes some training for dynamic group chat interactions</li>
|
| 270 |
+
<li>🎯 <strong>Perspective:</strong> Optimized for Male User → Female AI interactions</li>
|
| 271 |
+
<li>📖 <strong>Narrative Flow:</strong> Improved context retention with longer conversation threads in select scenarios</li>
|
| 272 |
+
</ul>
|
| 273 |
+
</div>
|
| 274 |
+
</details>
|
| 275 |
+
|
| 276 |
+
<details>
|
| 277 |
+
<summary>🧬 Synthetic Life Engine</summary>
|
| 278 |
+
<div class="mc-sec">
|
| 279 |
+
<p>Dataset generated using our advanced <strong>Character Engine</strong> and <strong>Emotional Engine</strong>, creating genuine life and emotional resonance in every interaction.</p>
|
| 280 |
+
<div class="mc-grid">
|
| 281 |
+
<div class="mc-card">
|
| 282 |
+
<h4>🎭 Character Engine</h4>
|
| 283 |
+
<p>Ensures consistent personality traits, speech patterns, and behavioral logic across all contexts. Characters remain true to themselves throughout.</p>
|
| 284 |
+
</div>
|
| 285 |
+
<div class="mc-card">
|
| 286 |
+
<h4>💓 Emotional Engine</h4>
|
| 287 |
+
<p>Injects dynamic emotional states into responses, creating depth and realistic reactions that breathe life into every exchange.</p>
|
| 288 |
+
</div>
|
| 289 |
+
<div class="mc-card">
|
| 290 |
+
<h4>✨ Quality Refinement</h4>
|
| 291 |
+
<p>Automated detection and rewriting of repetitive phrases ensures fresh, high-quality dialogue in every turn.</p>
|
| 292 |
+
</div>
|
| 293 |
+
<div class="mc-card">
|
| 294 |
+
<h4>💬 Dialogue Integrity</h4>
|
| 295 |
+
<p>Advanced quote normalization ensures balanced dialogue markers, preventing formatting errors and maintaining immersion.</p>
|
| 296 |
+
</div>
|
| 297 |
+
</div>
|
| 298 |
+
</div>
|
| 299 |
+
</details>
|
| 300 |
+
|
| 301 |
+
<details>
|
| 302 |
+
<summary>🧠 Training Details & Parameters</summary>
|
| 303 |
+
<div class="mc-sec">
|
| 304 |
+
<p>Fine-tuned using <strong>LoRA (Low-Rank Adaptation)</strong> for efficient and targeted weight adjustment, preserving the base model's capabilities while imprinting new behavioral patterns.</p>
|
| 305 |
+
<div class="mc-grid">
|
| 306 |
+
<div class="mc-card" style="text-align:center">
|
| 307 |
+
<h4>🔢 Epochs</h4>
|
| 308 |
+
<div class="mc-val">1</div>
|
| 309 |
+
<p class="mc-lbl">Full passes through the training dataset for thorough learning</p>
|
| 310 |
+
</div>
|
| 311 |
+
<div class="mc-card" style="text-align:center">
|
| 312 |
+
<h4>📐 LoRA Rank</h4>
|
| 313 |
+
<div class="mc-val">32</div>
|
| 314 |
+
<p class="mc-lbl">Optimized rank for balanced adaptation and efficiency</p>
|
| 315 |
+
</div>
|
| 316 |
+
</div>
|
| 317 |
+
<table class="mc-tbl">
|
| 318 |
+
<thead><tr><th>Parameter</th><th>Value</th></tr></thead>
|
| 319 |
+
<tbody>
|
| 320 |
+
<tr><td>Training Method</td><td><strong>LoRA (Low-Rank Adaptation)</strong></td></tr>
|
| 321 |
+
<tr><td>LoRA Rank (r)</td><td><strong>32</strong></td></tr>
|
| 322 |
+
<tr><td>Epochs</td><td><strong>1</strong></td></tr>
|
| 323 |
+
<tr><td>Trained Layers</td><td><strong>Text layers only</strong></td></tr>
|
| 324 |
+
<tr><td>Feature</td><td><strong>Group Chat Support</strong></td></tr>
|
| 325 |
+
</tbody>
|
| 326 |
+
</table>
|
| 327 |
+
<ul style="margin-top:18px">
|
| 328 |
+
<li>🎯 <strong>Method:</strong> LoRA fine-tuning for parameter-efficient adaptation, preserving base knowledge while imprinting new behaviors</li>
|
| 329 |
+
<li>⚡ <strong>Efficiency:</strong> Only a fraction of parameters updated, keeping the model lean and responsive</li>
|
| 330 |
+
<li>🎭 <strong>Result:</strong> Maintains coherence while exhibiting the desired personality traits and interaction style</li>
|
| 331 |
+
</ul>
|
| 332 |
+
</div>
|
| 333 |
+
</details>
|
| 334 |
+
|
| 335 |
+
<details>
|
| 336 |
+
<summary>🔮 Training Process</summary>
|
| 337 |
+
<div class="mc-sec">
|
| 338 |
+
<p>Model weights subjected to <strong>iterative refinement</strong> during data creation. Each conversation underwent multiple checks for stability and alignment.</p>
|
| 339 |
+
<ul>
|
| 340 |
+
<li>🔄 <strong>Multi-Turn Generation:</strong> Conversations built turn-by-turn for natural context flow</li>
|
| 341 |
+
<li>🛡️ <strong>Refusal Filtering:</strong> Automated systems detected and removed unwanted refusals</li>
|
| 342 |
+
<li>🧹 <strong>Slop Cleaning:</strong> Undesirable phrases identified and rewritten by dedicated assistant models</li>
|
| 343 |
+
<li>🎪 <strong>Group Chat Training:</strong> Includes some training data focused on multi-user group dynamics</li>
|
| 344 |
+
</ul>
|
| 345 |
+
</div>
|
| 346 |
+
</details>
|
| 347 |
+
|
| 348 |
+
<details>
|
| 349 |
+
<summary>📚 Dataset Overview</summary>
|
| 350 |
+
<div class="mc-sec">
|
| 351 |
+
<p>Model trained on a <strong>specialized adult-oriented roleplay dataset</strong> with diverse scenarios and emotional contexts, inspired by the spirit of Melody1437, though distinct in composition.</p>
|
| 352 |
+
<ul>
|
| 353 |
+
<li>🔞 <strong>Content Rating:</strong> Strictly 18+ (Adults Only)</li>
|
| 354 |
+
<li>📊 <strong>Dataset Size:</strong> Currently contains 12,211 specialized prompts.</li>
|
| 355 |
+
<li>📝 <strong>Conversation Depth:</strong> Portions include extended conversations for enhanced roleplay continuity.</li>
|
| 356 |
+
<li>🎭 <strong>Focus:</strong> Mature themes, immersive roleplay, uncensored dialogue</li>
|
| 357 |
+
<li>👥 <strong>Perspective:</strong> Male (User) → Female (AI)</li>
|
| 358 |
+
<li>🧹 <strong>Formatting:</strong> Removed Em dashes, asterisks, and markdown formatting from the dataset for cleaner output.</li>
|
| 359 |
+
</ul>
|
| 360 |
+
</div>
|
| 361 |
+
</details>
|
| 362 |
+
|
| 363 |
+
<details>
|
| 364 |
+
<summary>📜 Version Notes</summary>
|
| 365 |
+
<div class="mc-sec">
|
| 366 |
+
<ul>
|
| 367 |
+
<li>⚠️ <strong>Content Warning:</strong> This model can generate mature content. Use responsibly.</li>
|
| 368 |
+
<li>📉 <strong>Data Limitations:</strong> Trained on a curated dataset (12,211 prompts); performance may vary.</li>
|
| 369 |
+
<li>🧹 <strong>Clean Output:</strong> Reasoning tags, Em dashes, asterisks, and markdown formatting stripped for cleaner roleplay</li>
|
| 370 |
+
<li>🔀 <strong>Core Identity:</strong> Trained on the spirit of Melody1437, but utilizes a unique dataset</li>
|
| 371 |
+
<li>🎪 <strong>Feature:</strong> Includes some training for group chat scenarios</li>
|
| 372 |
+
<li>🔄 <strong>v2.0 Change:</strong> Same training data and configuration as v1.0, now applied to <strong>Gemma4-Gutenberg-31B</strong> as the base model for enhanced literary quality</li>
|
| 373 |
+
</ul>
|
| 374 |
+
</div>
|
| 375 |
+
</details>
|
| 376 |
+
|
| 377 |
+
<details>
|
| 378 |
+
<summary>⚙️ Configuration</summary>
|
| 379 |
+
<div class="mc-sec">
|
| 380 |
+
<div class="mc-qlinks">
|
| 381 |
+
<!-- Sampler Settings Box -->
|
| 382 |
+
<div class="mc-card">
|
| 383 |
+
<h4>🎛️ Sampler Settings</h4>
|
| 384 |
+
<p style="margin-bottom:12px;font-size:.78em;color:#8a7f90">Recommended parameters for optimal output</p>
|
| 385 |
+
<div class="sampler-grid">
|
| 386 |
+
<div class="param-box">
|
| 387 |
+
<span class="param-val">0.92</span>
|
| 388 |
+
<span class="param-label">Top-P</span>
|
| 389 |
+
</div>
|
| 390 |
+
<div class="param-box">
|
| 391 |
+
<span class="param-val">1.0</span>
|
| 392 |
+
<span class="param-label">Temperature</span>
|
| 393 |
+
</div>
|
| 394 |
+
<div class="param-box">
|
| 395 |
+
<span class="param-val">0</span>
|
| 396 |
+
<span class="param-label">Freq Pen</span>
|
| 397 |
+
</div>
|
| 398 |
+
<div class="param-box">
|
| 399 |
+
<span class="param-val">0</span>
|
| 400 |
+
<span class="param-label">Presence Pen</span>
|
| 401 |
+
</div>
|
| 402 |
+
</div>
|
| 403 |
+
</div>
|
| 404 |
+
<!-- GGUF Download Box -->
|
| 405 |
+
<div class="mc-card">
|
| 406 |
+
<h4>📦 GGUF Quantizations</h4>
|
| 407 |
+
<p style="font-size:.78em;color:#8a7f90">Available formats for local inference</p>
|
| 408 |
+
<ul class="quant-list">
|
| 409 |
+
<li class="quant-item"><span>Q4_K_M</span><span>Decent Quality</span></li>
|
| 410 |
+
<li class="quant-item"><span>Q5_K_M</span><span>Recommended</span></li>
|
| 411 |
+
<li class="quant-item"><span>Q6_K</span><span>High Quality</span></li>
|
| 412 |
+
<li class="quant-item"><span>Q8_0</span><span>Near Lossless</span></li>
|
| 413 |
+
</ul>
|
| 414 |
+
<a href="https://huggingface.co/ReadyArt/Dark-Scarlett-v2.0-31B-GGUF" class="mc-btn mc-btn-glow">
|
| 415 |
+
<span class="download-icon">⬇</span> View Repository
|
| 416 |
+
</a>
|
| 417 |
+
</div>
|
| 418 |
+
</div>
|
| 419 |
+
</div>
|
| 420 |
+
</details>
|
| 421 |
+
|
| 422 |
+
<details>
|
| 423 |
+
<summary>💖 Credits</summary>
|
| 424 |
+
<div class="mc-sec">
|
| 425 |
+
<ul>
|
| 426 |
+
<li style="display:flex;align-items:center;margin-bottom:14px;padding:18px 22px;background:linear-gradient(145deg,#0f0c14,#0c0a10);border:1px solid rgba(255,42,109,.12);border-radius:14px;transition:all 0.3s">
|
| 427 |
+
<img src="https://huggingface.co/avatars/55f24699e05af4295a9d16ddecd81f8a.svg" alt="GECFDO" class="mc-ava">
|
| 428 |
+
<span><strong>GECFDO</strong> — Dataset Generation</span>
|
| 429 |
+
</li>
|
| 430 |
+
<li style="display:flex;align-items:center;margin-bottom:14px;padding:18px 22px;background:linear-gradient(145deg,#0f0c14,#0c0a10);border:1px solid rgba(255,42,109,.12);border-radius:14px;transition:all 0.3s">
|
| 431 |
+
<img src="https://cdn-avatars.huggingface.co/v1/production/uploads/6759e155bc947d6070775cb9/FW3jKJ-t8iH9MPGeWzyX5.png" alt="FrenzyBiscuit" class="mc-ava">
|
| 432 |
+
<span><strong>FrenzyBiscuit</strong> — Fine-Tuning & Dataset Creation</span>
|
| 433 |
+
</li>
|
| 434 |
+
</ul>
|
| 435 |
+
</div>
|
| 436 |
+
</details>
|
| 437 |
+
|
| 438 |
+
<div class="mc-ornament"><span>⟡</span></div>
|
| 439 |
+
|
| 440 |
+
<div class="mc-sec">
|
| 441 |
+
<h2 class="mc-sec-title">🔖 License & Usage</h2>
|
| 442 |
+
<div class="mc-disclaimer">
|
| 443 |
+
<strong>⚠️ Usage Agreement:</strong> By using this model, you accept all terms and conditions.
|
| 444 |
+
</div>
|
| 445 |
+
<ul>
|
| 446 |
+
<li>🛡️ You accept <strong>full responsibility</strong> for all outputs generated</li>
|
| 447 |
+
<li>🔞 You confirm you are at least <strong>18 years old</strong></li>
|
| 448 |
+
<li>🌍 Creators bear <strong>no responsibility</strong> for how the model is used</li>
|
| 449 |
+
<li>🏡 For <strong>personal use only</strong> (non-profit/non-commercial) to the extent legally allowed</li>
|
| 450 |
+
<li>Apache-2.0 (matching the Gemma 4 base). Constituent training datasets carry their own licenses (see the Athanorlite-DPO card on the nbeerbower/Gemma4-Gutenberg-31 model).</li>
|
| 451 |
+
</ul>
|
| 452 |
+
<div class="mc-tag-container" style="justify-content:flex-start;margin-top:22px">
|
| 453 |
+
<span class="mc-tag t1">Apache 2.0</span>
|
| 454 |
+
<span class="mc-tag t2">Personal Use</span>
|
| 455 |
+
<span class="mc-tag t-nsfw">18+ Content</span>
|
| 456 |
+
<span class="mc-tag t4">NSFW</span>
|
| 457 |
+
</div>
|
| 458 |
+
</div>
|
| 459 |
+
|
| 460 |
+
</div>
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,390 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#
|
| 2 |
+
Template: Google Gemma 4 Canonical Chat Template
|
| 3 |
+
Author: Google Gemma Engineering Team
|
| 4 |
+
Published: 2026-07-09
|
| 5 |
+
Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
|
| 6 |
+
#}
|
| 7 |
+
{%- macro format_parameters(properties, required, filter_keys=false) -%}
|
| 8 |
+
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
|
| 9 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 10 |
+
{%- for key, value in properties | dictsort -%}
|
| 11 |
+
{%- set add_comma = false -%}
|
| 12 |
+
{%- if not filter_keys or key not in standard_keys -%}
|
| 13 |
+
{%- if ns.found_first %},{% endif -%}
|
| 14 |
+
{%- set ns.found_first = true -%}
|
| 15 |
+
{{ key }}:{
|
| 16 |
+
{%- if value['description'] -%}
|
| 17 |
+
description:<|"|>{{ value['description'] }}<|"|>
|
| 18 |
+
{%- set add_comma = true -%}
|
| 19 |
+
{%- endif -%}
|
| 20 |
+
{%- if value['type'] | upper == 'STRING' -%}
|
| 21 |
+
{%- if value['enum'] -%}
|
| 22 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 23 |
+
enum:{{ format_argument(value['enum']) }}
|
| 24 |
+
{%- endif -%}
|
| 25 |
+
{%- elif value['type'] | upper == 'ARRAY' -%}
|
| 26 |
+
{%- if value['items'] is mapping and value['items'] -%}
|
| 27 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 28 |
+
items:{
|
| 29 |
+
{%- set ns_items = namespace(found_first=false) -%}
|
| 30 |
+
{%- for item_key, item_value in value['items'] | dictsort -%}
|
| 31 |
+
{%- if item_value is not none -%}
|
| 32 |
+
{%- if ns_items.found_first %},{% endif -%}
|
| 33 |
+
{%- set ns_items.found_first = true -%}
|
| 34 |
+
{%- if item_key == 'properties' -%}
|
| 35 |
+
properties:{
|
| 36 |
+
{%- if item_value is mapping -%}
|
| 37 |
+
{{- format_parameters(item_value, value['items']['required'] | default([])) -}}
|
| 38 |
+
{%- endif -%}
|
| 39 |
+
}
|
| 40 |
+
{%- elif item_key == 'required' -%}
|
| 41 |
+
required:[
|
| 42 |
+
{%- for req_item in item_value -%}
|
| 43 |
+
<|"|>{{- req_item -}}<|"|>
|
| 44 |
+
{%- if not loop.last %},{% endif -%}
|
| 45 |
+
{%- endfor -%}
|
| 46 |
+
]
|
| 47 |
+
{%- elif item_key == 'type' -%}
|
| 48 |
+
{%- if item_value is string -%}
|
| 49 |
+
type:{{ format_argument(item_value | upper) }}
|
| 50 |
+
{%- else -%}
|
| 51 |
+
type:{{ format_argument(item_value | map('upper') | list) }}
|
| 52 |
+
{%- endif -%}
|
| 53 |
+
{%- else -%}
|
| 54 |
+
{{ item_key }}:{{ format_argument(item_value) }}
|
| 55 |
+
{%- endif -%}
|
| 56 |
+
{%- endif -%}
|
| 57 |
+
{%- endfor -%}
|
| 58 |
+
}
|
| 59 |
+
{%- endif -%}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if value['nullable'] %}
|
| 62 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 63 |
+
nullable:true
|
| 64 |
+
{%- endif -%}
|
| 65 |
+
{%- if value['type'] | upper == 'OBJECT' -%}
|
| 66 |
+
{%- if value['properties'] is defined and value['properties'] is mapping -%}
|
| 67 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 68 |
+
properties:{
|
| 69 |
+
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
|
| 70 |
+
}
|
| 71 |
+
{%- elif value is mapping -%}
|
| 72 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 73 |
+
properties:{
|
| 74 |
+
{{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
|
| 75 |
+
}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- if value['required'] -%}
|
| 78 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 79 |
+
required:[
|
| 80 |
+
{%- for item in value['required'] | default([]) -%}
|
| 81 |
+
<|"|>{{- item -}}<|"|>
|
| 82 |
+
{%- if not loop.last %},{% endif -%}
|
| 83 |
+
{%- endfor -%}
|
| 84 |
+
]
|
| 85 |
+
{%- endif -%}
|
| 86 |
+
{%- endif -%}
|
| 87 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 88 |
+
type:<|"|>{{ value['type'] | upper }}<|"|>}
|
| 89 |
+
{%- endif -%}
|
| 90 |
+
{%- endfor -%}
|
| 91 |
+
{%- endmacro -%}
|
| 92 |
+
{%- macro format_function_declaration(tool_data) -%}
|
| 93 |
+
declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
|
| 94 |
+
{%- set params = tool_data['function']['parameters'] -%}
|
| 95 |
+
{%- if params -%}
|
| 96 |
+
,parameters:{
|
| 97 |
+
{%- if params['properties'] -%}
|
| 98 |
+
properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
|
| 99 |
+
{%- endif -%}
|
| 100 |
+
{%- if params['required'] -%}
|
| 101 |
+
required:[
|
| 102 |
+
{%- for item in params['required'] -%}
|
| 103 |
+
<|"|>{{- item -}}<|"|>
|
| 104 |
+
{{- ',' if not loop.last -}}
|
| 105 |
+
{%- endfor -%}
|
| 106 |
+
],
|
| 107 |
+
{%- endif -%}
|
| 108 |
+
{%- if params['type'] -%}
|
| 109 |
+
type:<|"|>{{- params['type'] | upper -}}<|"|>}
|
| 110 |
+
{%- endif -%}
|
| 111 |
+
{%- endif -%}
|
| 112 |
+
{%- if 'response' in tool_data['function'] -%}
|
| 113 |
+
{%- set response_declaration = tool_data['function']['response'] -%}
|
| 114 |
+
,response:{
|
| 115 |
+
{%- if response_declaration['description'] -%}
|
| 116 |
+
description:<|"|>{{- response_declaration['description'] -}}<|"|>,
|
| 117 |
+
{%- endif -%}
|
| 118 |
+
{%- if response_declaration['type'] | upper == 'OBJECT' -%}
|
| 119 |
+
type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
|
| 120 |
+
{%- endif -%}
|
| 121 |
+
{%- endif -%}
|
| 122 |
+
}
|
| 123 |
+
{%- endmacro -%}
|
| 124 |
+
{%- macro format_argument(argument, escape_keys=True) -%}
|
| 125 |
+
{%- if argument is none -%}
|
| 126 |
+
{{- 'null' -}}
|
| 127 |
+
{%- elif argument is string -%}
|
| 128 |
+
{{- '<|"|>' + argument + '<|"|>' -}}
|
| 129 |
+
{%- elif argument is boolean -%}
|
| 130 |
+
{{- 'true' if argument else 'false' -}}
|
| 131 |
+
{%- elif argument is mapping -%}
|
| 132 |
+
{{- '{' -}}
|
| 133 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 134 |
+
{%- for key, value in argument | dictsort -%}
|
| 135 |
+
{%- if ns.found_first %},{% endif -%}
|
| 136 |
+
{%- set ns.found_first = true -%}
|
| 137 |
+
{%- if escape_keys -%}
|
| 138 |
+
{{- '<|"|>' + key + '<|"|>' -}}
|
| 139 |
+
{%- else -%}
|
| 140 |
+
{{- key -}}
|
| 141 |
+
{%- endif -%}
|
| 142 |
+
:{{- format_argument(value, escape_keys=escape_keys) -}}
|
| 143 |
+
{%- endfor -%}
|
| 144 |
+
{{- '}' -}}
|
| 145 |
+
{%- elif argument is sequence -%}
|
| 146 |
+
{{- '[' -}}
|
| 147 |
+
{%- for item in argument -%}
|
| 148 |
+
{{- format_argument(item, escape_keys=escape_keys) -}}
|
| 149 |
+
{%- if not loop.last %},{% endif -%}
|
| 150 |
+
{%- endfor -%}
|
| 151 |
+
{{- ']' -}}
|
| 152 |
+
{%- else -%}
|
| 153 |
+
{{- argument -}}
|
| 154 |
+
{%- endif -%}
|
| 155 |
+
{%- endmacro -%}
|
| 156 |
+
{%- macro strip_thinking(text) -%}
|
| 157 |
+
{%- set ns = namespace(result='') -%}
|
| 158 |
+
{%- for part in text.split('<channel|>') -%}
|
| 159 |
+
{%- if '<|channel>' in part -%}
|
| 160 |
+
{%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
|
| 161 |
+
{%- else -%}
|
| 162 |
+
{%- set ns.result = ns.result + part -%}
|
| 163 |
+
{%- endif -%}
|
| 164 |
+
{%- endfor -%}
|
| 165 |
+
{{- ns.result | trim -}}
|
| 166 |
+
{%- endmacro -%}
|
| 167 |
+
|
| 168 |
+
{%- macro format_tool_response_block(tool_name, response) -%}
|
| 169 |
+
{{- '<|tool_response>' -}}
|
| 170 |
+
{%- if response is mapping -%}
|
| 171 |
+
{{- 'response:' + tool_name + '{' -}}
|
| 172 |
+
{%- for key, value in response | dictsort -%}
|
| 173 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 174 |
+
{%- if not loop.last %},{% endif -%}
|
| 175 |
+
{%- endfor -%}
|
| 176 |
+
{{- '}' -}}
|
| 177 |
+
{%- else -%}
|
| 178 |
+
{{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
|
| 179 |
+
{%- endif -%}
|
| 180 |
+
{{- '<tool_response|>' -}}
|
| 181 |
+
{%- endmacro -%}
|
| 182 |
+
|
| 183 |
+
{#- ===== SETUP ===== -#}
|
| 184 |
+
{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
|
| 185 |
+
{%- set loop_messages = messages -%}
|
| 186 |
+
{%- set enable_thinking = enable_thinking | default(false) -%}
|
| 187 |
+
{%- set preserve_thinking = preserve_thinking | default(false) -%}
|
| 188 |
+
{{- bos_token -}}
|
| 189 |
+
{#- Handle System/Tool Definitions Block -#}
|
| 190 |
+
{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
|
| 191 |
+
{{- '<|turn>system\n' -}}
|
| 192 |
+
{#- Inject Thinking token at the very top of the FIRST system turn -#}
|
| 193 |
+
{%- if enable_thinking -%}
|
| 194 |
+
{{- '<|think|>\n' -}}
|
| 195 |
+
{%- set ns.prev_message_type = 'think' -%}
|
| 196 |
+
{%- endif -%}
|
| 197 |
+
{%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
|
| 198 |
+
{%- if messages[0]['content'] is string -%}
|
| 199 |
+
{{- messages[0]['content'] | trim -}}
|
| 200 |
+
{%- elif messages[0]['content'] is sequence -%}
|
| 201 |
+
{%- for item in messages[0]['content'] -%}
|
| 202 |
+
{{- item['text'] | trim + ' '-}}
|
| 203 |
+
{%- endfor -%}
|
| 204 |
+
{%- endif -%}
|
| 205 |
+
{%- set loop_messages = messages[1:] -%}
|
| 206 |
+
{%- endif -%}
|
| 207 |
+
{%- if tools -%}
|
| 208 |
+
{%- for tool in tools %}
|
| 209 |
+
{{- '<|tool>' -}}
|
| 210 |
+
{{- format_function_declaration(tool) | trim -}}
|
| 211 |
+
{{- '<tool|>' -}}
|
| 212 |
+
{%- endfor %}
|
| 213 |
+
{%- set ns.prev_message_type = 'tool' -%}
|
| 214 |
+
{%- endif -%}
|
| 215 |
+
{{- '<turn|>\n' -}}
|
| 216 |
+
{%- endif %}
|
| 217 |
+
|
| 218 |
+
{#- Pre-scan: find last user message index for reasoning guard -#}
|
| 219 |
+
{%- set ns_turn = namespace(last_user_idx=-1) -%}
|
| 220 |
+
{%- for i in range(loop_messages | length) -%}
|
| 221 |
+
{%- if loop_messages[i]['role'] == 'user' -%}
|
| 222 |
+
{%- set ns_turn.last_user_idx = i -%}
|
| 223 |
+
{%- endif -%}
|
| 224 |
+
{%- endfor -%}
|
| 225 |
+
|
| 226 |
+
{#- Loop through messages -#}
|
| 227 |
+
{%- for message in loop_messages -%}
|
| 228 |
+
{%- if message['role'] != 'tool' -%}
|
| 229 |
+
{%- set ns.prev_message_type = None -%}
|
| 230 |
+
{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
|
| 231 |
+
{#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
|
| 232 |
+
{%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
|
| 233 |
+
{%- if not continue_same_model_turn -%}
|
| 234 |
+
{{- '<|turn>' + role + '\n' }}
|
| 235 |
+
|
| 236 |
+
{%- endif -%}
|
| 237 |
+
|
| 238 |
+
{#- Render reasoning/reasoning_content as thinking channel -#}
|
| 239 |
+
{%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
|
| 240 |
+
{%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
|
| 241 |
+
{%- if thinking_text and thinking_gate -%}
|
| 242 |
+
{{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
|
| 243 |
+
{%- endif -%}
|
| 244 |
+
|
| 245 |
+
{%- if message.get('tool_calls') -%}
|
| 246 |
+
{%- for tool_call in message.get('tool_calls') -%}
|
| 247 |
+
{%- set function = tool_call['function'] -%}
|
| 248 |
+
{{- '<|tool_call>call:' + function['name'] + '{' -}}
|
| 249 |
+
{%- if function['arguments'] is mapping -%}
|
| 250 |
+
{%- set ns_args = namespace(found_first=false) -%}
|
| 251 |
+
{%- for key, value in function['arguments'] | dictsort -%}
|
| 252 |
+
{%- if ns_args.found_first %},{% endif -%}
|
| 253 |
+
{%- set ns_args.found_first = true -%}
|
| 254 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 255 |
+
{%- endfor -%}
|
| 256 |
+
{%- elif function['arguments'] is none -%}
|
| 257 |
+
{%- else -%}
|
| 258 |
+
{{- raise_exception(
|
| 259 |
+
"chat_template: tool_calls[].function.arguments must be a "
|
| 260 |
+
"JSON object (mapping), not a string. Deserialize arguments "
|
| 261 |
+
"before passing to the template."
|
| 262 |
+
) -}}
|
| 263 |
+
{%- endif -%}
|
| 264 |
+
{{- '}<tool_call|>' -}}
|
| 265 |
+
{%- endfor -%}
|
| 266 |
+
{%- set ns.prev_message_type = 'tool_call' -%}
|
| 267 |
+
{%- endif -%}
|
| 268 |
+
|
| 269 |
+
{%- set ns_tr_out = namespace(flag=false) -%}
|
| 270 |
+
{%- if message.get('tool_responses') -%}
|
| 271 |
+
{#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
|
| 272 |
+
{%- for tool_response in message.get('tool_responses') -%}
|
| 273 |
+
{{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
|
| 274 |
+
{%- set ns_tr_out.flag = true -%}
|
| 275 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 276 |
+
{%- endfor -%}
|
| 277 |
+
{%- elif message.get('tool_calls') -%}
|
| 278 |
+
{#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
|
| 279 |
+
{%- set ns_tool_scan = namespace(stopped=false) -%}
|
| 280 |
+
{%- for k in range(loop.index0 + 1, loop_messages | length) -%}
|
| 281 |
+
{%- if ns_tool_scan.stopped -%}
|
| 282 |
+
{%- elif loop_messages[k]['role'] != 'tool' -%}
|
| 283 |
+
{%- set ns_tool_scan.stopped = true -%}
|
| 284 |
+
{%- else -%}
|
| 285 |
+
{%- set follow = loop_messages[k] -%}
|
| 286 |
+
{#- Resolve tool_call_id to function name -#}
|
| 287 |
+
{%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
|
| 288 |
+
{%- for tc in message.get('tool_calls') -%}
|
| 289 |
+
{%- if tc.get('id') == follow.get('tool_call_id') -%}
|
| 290 |
+
{%- set ns_tname.name = tc['function']['name'] -%}
|
| 291 |
+
{%- endif -%}
|
| 292 |
+
{%- endfor -%}
|
| 293 |
+
{#- Handle content as string or content-parts array -#}
|
| 294 |
+
{%- set tool_body = follow.get('content') -%}
|
| 295 |
+
{%- if tool_body is string -%}
|
| 296 |
+
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
| 297 |
+
{%- elif tool_body is sequence and tool_body is not string -%}
|
| 298 |
+
{%- set ns_txt = namespace(s='') -%}
|
| 299 |
+
{%- for part in tool_body -%}
|
| 300 |
+
{%- if part.get('type') == 'text' -%}
|
| 301 |
+
{%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
|
| 302 |
+
{%- endif -%}
|
| 303 |
+
{%- endfor -%}
|
| 304 |
+
{{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
|
| 305 |
+
{%- for part in tool_body -%}
|
| 306 |
+
{%- if part.get('type') in ['image', 'image_url'] -%}
|
| 307 |
+
{{- '<|image|>' -}}
|
| 308 |
+
{%- elif part.get('type') in ['audio', 'input_audio'] -%}
|
| 309 |
+
{{- '<|audio|>' -}}
|
| 310 |
+
{%- elif part.get('type') == 'video' -%}
|
| 311 |
+
{{- '<|video|>' -}}
|
| 312 |
+
{%- endif -%}
|
| 313 |
+
{%- endfor -%}
|
| 314 |
+
{%- else -%}
|
| 315 |
+
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
| 316 |
+
{%- endif -%}
|
| 317 |
+
{%- set ns_tr_out.flag = true -%}
|
| 318 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 319 |
+
{%- endif -%}
|
| 320 |
+
{%- endfor -%}
|
| 321 |
+
{%- endif -%}
|
| 322 |
+
|
| 323 |
+
{%- set captured_content -%}
|
| 324 |
+
{%- if message.get('content') is string -%}
|
| 325 |
+
{%- if role == 'model' -%}
|
| 326 |
+
{{- strip_thinking(message['content']) -}}
|
| 327 |
+
{%- else -%}
|
| 328 |
+
{{- message['content'] | trim -}}
|
| 329 |
+
{%- endif -%}
|
| 330 |
+
{%- elif message.get('content') is sequence -%}
|
| 331 |
+
{%- for item in message['content'] -%}
|
| 332 |
+
{%- if item.get('type') == 'text' -%}
|
| 333 |
+
{%- if role == 'model' -%}
|
| 334 |
+
{{- strip_thinking(item['text']) -}}
|
| 335 |
+
{%- else -%}
|
| 336 |
+
{{- item['text'] | trim -}}
|
| 337 |
+
{%- endif -%}
|
| 338 |
+
{%- elif item.get('type') in ['image', 'image_url'] -%}
|
| 339 |
+
{{- '<|image|>' -}}
|
| 340 |
+
{%- elif item.get('type') in ['audio', 'input_audio'] -%}
|
| 341 |
+
{{- '<|audio|>' -}}
|
| 342 |
+
{%- elif item.get('type') == 'video' -%}
|
| 343 |
+
{{- '<|video|>' -}}
|
| 344 |
+
{%- endif -%}
|
| 345 |
+
{%- endfor -%}
|
| 346 |
+
{%- endif -%}
|
| 347 |
+
{%- endset -%}
|
| 348 |
+
|
| 349 |
+
{{- captured_content -}}
|
| 350 |
+
{%- set has_content = captured_content | trim | length > 0 -%}
|
| 351 |
+
|
| 352 |
+
{#- Forward-scan: find next non-tool message role for continuation detection -#}
|
| 353 |
+
{%- set next_nt = namespace(role=None, found=false) -%}
|
| 354 |
+
{%- for j in range(loop.index0 + 1, loop_messages | length) -%}
|
| 355 |
+
{%- if not next_nt.found -%}
|
| 356 |
+
{%- if loop_messages[j]['role'] != 'tool' -%}
|
| 357 |
+
{%- set next_nt.role = loop_messages[j]['role'] -%}
|
| 358 |
+
{%- set next_nt.found = true -%}
|
| 359 |
+
{%- endif -%}
|
| 360 |
+
{%- endif -%}
|
| 361 |
+
{%- endfor -%}
|
| 362 |
+
|
| 363 |
+
{%- set continues_into_next = (
|
| 364 |
+
role == 'model'
|
| 365 |
+
and next_nt.role == 'assistant'
|
| 366 |
+
and (not message.get('tool_calls') or ns_tr_out.flag)
|
| 367 |
+
) -%}
|
| 368 |
+
|
| 369 |
+
{%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
|
| 370 |
+
{{- '<|tool_response>' -}}
|
| 371 |
+
{%- elif continues_into_next -%}
|
| 372 |
+
{%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
|
| 373 |
+
{{- '<turn|>\n' -}}
|
| 374 |
+
{%- endif -%}
|
| 375 |
+
|
| 376 |
+
{#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
|
| 377 |
+
{%- set ns.prev_non_tool_role = message['role'] -%}
|
| 378 |
+
{%- endif -%}
|
| 379 |
+
{%- endfor -%}
|
| 380 |
+
|
| 381 |
+
{%- if add_generation_prompt -%}
|
| 382 |
+
{%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
|
| 383 |
+
{{- '<|turn>model\n' -}}
|
| 384 |
+
{%- if not enable_thinking -%}
|
| 385 |
+
{{- '<|channel>thought\n<channel|>' -}}
|
| 386 |
+
{%- endif -%}
|
| 387 |
+
{%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
|
| 388 |
+
{{- '<|channel>thought\n' -}}
|
| 389 |
+
{%- endif -%}
|
| 390 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,978 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": null,
|
| 6 |
+
"audio_token_id": 258881,
|
| 7 |
+
"boa_token_id": 256000,
|
| 8 |
+
"boi_token_id": 255999,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eoa_token_id": 258883,
|
| 11 |
+
"eoa_token_index": 258883,
|
| 12 |
+
"eoi_token_id": 258882,
|
| 13 |
+
"eos_token_id": [
|
| 14 |
+
1,
|
| 15 |
+
106,
|
| 16 |
+
50
|
| 17 |
+
],
|
| 18 |
+
"image_token_id": 258880,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"model_type": "gemma4",
|
| 21 |
+
"text_config": {
|
| 22 |
+
"attention_bias": false,
|
| 23 |
+
"attention_dropout": 0.0,
|
| 24 |
+
"attention_k_eq_v": true,
|
| 25 |
+
"bos_token_id": 2,
|
| 26 |
+
"dtype": "bfloat16",
|
| 27 |
+
"enable_moe_block": false,
|
| 28 |
+
"eos_token_id": 1,
|
| 29 |
+
"expert_intermediate_size": null,
|
| 30 |
+
"final_logit_softcapping": 30.0,
|
| 31 |
+
"global_head_dim": 512,
|
| 32 |
+
"head_dim": 256,
|
| 33 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 34 |
+
"hidden_size": 5376,
|
| 35 |
+
"hidden_size_per_layer_input": 0,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 21504,
|
| 38 |
+
"layer_types": [
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"sliding_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"sliding_attention",
|
| 72 |
+
"sliding_attention",
|
| 73 |
+
"sliding_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"sliding_attention",
|
| 76 |
+
"sliding_attention",
|
| 77 |
+
"sliding_attention",
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"sliding_attention",
|
| 80 |
+
"full_attention",
|
| 81 |
+
"sliding_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"sliding_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"sliding_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"sliding_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"sliding_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"sliding_attention",
|
| 92 |
+
"full_attention",
|
| 93 |
+
"sliding_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"sliding_attention",
|
| 96 |
+
"sliding_attention",
|
| 97 |
+
"sliding_attention",
|
| 98 |
+
"full_attention"
|
| 99 |
+
],
|
| 100 |
+
"max_position_embeddings": 262144,
|
| 101 |
+
"model_type": "gemma4_text",
|
| 102 |
+
"moe_intermediate_size": null,
|
| 103 |
+
"num_attention_heads": 32,
|
| 104 |
+
"num_experts": null,
|
| 105 |
+
"num_global_key_value_heads": 4,
|
| 106 |
+
"num_hidden_layers": 60,
|
| 107 |
+
"num_key_value_heads": 16,
|
| 108 |
+
"num_kv_shared_layers": 0,
|
| 109 |
+
"pad_token_id": 0,
|
| 110 |
+
"rms_norm_eps": 1e-06,
|
| 111 |
+
"rope_parameters": {
|
| 112 |
+
"full_attention": {
|
| 113 |
+
"partial_rotary_factor": 0.25,
|
| 114 |
+
"rope_theta": 1000000.0,
|
| 115 |
+
"rope_type": "proportional"
|
| 116 |
+
},
|
| 117 |
+
"sliding_attention": {
|
| 118 |
+
"rope_theta": 10000.0,
|
| 119 |
+
"rope_type": "default"
|
| 120 |
+
}
|
| 121 |
+
},
|
| 122 |
+
"sliding_window": 1024,
|
| 123 |
+
"tie_word_embeddings": true,
|
| 124 |
+
"top_k_experts": null,
|
| 125 |
+
"use_bidirectional_attention": "vision",
|
| 126 |
+
"use_cache": true,
|
| 127 |
+
"use_double_wide_mlp": false,
|
| 128 |
+
"vocab_size": 262144,
|
| 129 |
+
"vocab_size_per_layer_input": 262144
|
| 130 |
+
},
|
| 131 |
+
"tie_word_embeddings": true,
|
| 132 |
+
"transformers_version": "5.8.0",
|
| 133 |
+
"video_token_id": 258884,
|
| 134 |
+
"vision_config": {
|
| 135 |
+
"_name_or_path": "",
|
| 136 |
+
"architectures": null,
|
| 137 |
+
"attention_bias": false,
|
| 138 |
+
"attention_dropout": 0.0,
|
| 139 |
+
"chunk_size_feed_forward": 0,
|
| 140 |
+
"default_output_length": 280,
|
| 141 |
+
"dtype": "bfloat16",
|
| 142 |
+
"global_head_dim": 72,
|
| 143 |
+
"head_dim": 72,
|
| 144 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 145 |
+
"hidden_size": 1152,
|
| 146 |
+
"id2label": {
|
| 147 |
+
"0": "LABEL_0",
|
| 148 |
+
"1": "LABEL_1"
|
| 149 |
+
},
|
| 150 |
+
"initializer_range": 0.02,
|
| 151 |
+
"intermediate_size": 4304,
|
| 152 |
+
"is_encoder_decoder": false,
|
| 153 |
+
"label2id": {
|
| 154 |
+
"LABEL_0": 0,
|
| 155 |
+
"LABEL_1": 1
|
| 156 |
+
},
|
| 157 |
+
"max_position_embeddings": 131072,
|
| 158 |
+
"model_type": "gemma4_vision",
|
| 159 |
+
"num_attention_heads": 16,
|
| 160 |
+
"num_hidden_layers": 27,
|
| 161 |
+
"num_key_value_heads": 16,
|
| 162 |
+
"output_attentions": false,
|
| 163 |
+
"output_hidden_states": false,
|
| 164 |
+
"patch_size": 16,
|
| 165 |
+
"pooling_kernel_size": 3,
|
| 166 |
+
"position_embedding_size": 10240,
|
| 167 |
+
"problem_type": null,
|
| 168 |
+
"return_dict": true,
|
| 169 |
+
"rms_norm_eps": 1e-06,
|
| 170 |
+
"rope_parameters": {
|
| 171 |
+
"rope_theta": 100.0,
|
| 172 |
+
"rope_type": "default"
|
| 173 |
+
},
|
| 174 |
+
"standardize": true,
|
| 175 |
+
"use_clipped_linears": false
|
| 176 |
+
},
|
| 177 |
+
"vision_soft_tokens_per_image": 280,
|
| 178 |
+
"quantization_config": {
|
| 179 |
+
"quant_method": "compressed-tensors",
|
| 180 |
+
"format": "float-quantized",
|
| 181 |
+
"config_groups": {
|
| 182 |
+
"group_0": {
|
| 183 |
+
"weights": {
|
| 184 |
+
"num_bits": 8,
|
| 185 |
+
"type": "float",
|
| 186 |
+
"symmetric": true,
|
| 187 |
+
"strategy": "channel",
|
| 188 |
+
"dynamic": false
|
| 189 |
+
},
|
| 190 |
+
"input_activations": null,
|
| 191 |
+
"targets": [
|
| 192 |
+
"Linear"
|
| 193 |
+
]
|
| 194 |
+
}
|
| 195 |
+
},
|
| 196 |
+
"ignore": [
|
| 197 |
+
"model.embed_vision.embedding_projection",
|
| 198 |
+
"model.language_model.embed_tokens",
|
| 199 |
+
"model.language_model.layers.0.input_layernorm",
|
| 200 |
+
"model.language_model.layers.0.layer_scalar",
|
| 201 |
+
"model.language_model.layers.0.post_attention_layernorm",
|
| 202 |
+
"model.language_model.layers.0.post_feedforward_layernorm",
|
| 203 |
+
"model.language_model.layers.0.pre_feedforward_layernorm",
|
| 204 |
+
"model.language_model.layers.0.self_attn.k_norm",
|
| 205 |
+
"model.language_model.layers.0.self_attn.q_norm",
|
| 206 |
+
"model.language_model.layers.1.input_layernorm",
|
| 207 |
+
"model.language_model.layers.1.layer_scalar",
|
| 208 |
+
"model.language_model.layers.1.post_attention_layernorm",
|
| 209 |
+
"model.language_model.layers.1.post_feedforward_layernorm",
|
| 210 |
+
"model.language_model.layers.1.pre_feedforward_layernorm",
|
| 211 |
+
"model.language_model.layers.1.self_attn.k_norm",
|
| 212 |
+
"model.language_model.layers.1.self_attn.q_norm",
|
| 213 |
+
"model.language_model.layers.10.input_layernorm",
|
| 214 |
+
"model.language_model.layers.10.layer_scalar",
|
| 215 |
+
"model.language_model.layers.10.post_attention_layernorm",
|
| 216 |
+
"model.language_model.layers.10.post_feedforward_layernorm",
|
| 217 |
+
"model.language_model.layers.10.pre_feedforward_layernorm",
|
| 218 |
+
"model.language_model.layers.10.self_attn.k_norm",
|
| 219 |
+
"model.language_model.layers.10.self_attn.q_norm",
|
| 220 |
+
"model.language_model.layers.11.input_layernorm",
|
| 221 |
+
"model.language_model.layers.11.layer_scalar",
|
| 222 |
+
"model.language_model.layers.11.post_attention_layernorm",
|
| 223 |
+
"model.language_model.layers.11.post_feedforward_layernorm",
|
| 224 |
+
"model.language_model.layers.11.pre_feedforward_layernorm",
|
| 225 |
+
"model.language_model.layers.11.self_attn.k_norm",
|
| 226 |
+
"model.language_model.layers.11.self_attn.q_norm",
|
| 227 |
+
"model.language_model.layers.12.input_layernorm",
|
| 228 |
+
"model.language_model.layers.12.layer_scalar",
|
| 229 |
+
"model.language_model.layers.12.post_attention_layernorm",
|
| 230 |
+
"model.language_model.layers.12.post_feedforward_layernorm",
|
| 231 |
+
"model.language_model.layers.12.pre_feedforward_layernorm",
|
| 232 |
+
"model.language_model.layers.12.self_attn.k_norm",
|
| 233 |
+
"model.language_model.layers.12.self_attn.q_norm",
|
| 234 |
+
"model.language_model.layers.13.input_layernorm",
|
| 235 |
+
"model.language_model.layers.13.layer_scalar",
|
| 236 |
+
"model.language_model.layers.13.post_attention_layernorm",
|
| 237 |
+
"model.language_model.layers.13.post_feedforward_layernorm",
|
| 238 |
+
"model.language_model.layers.13.pre_feedforward_layernorm",
|
| 239 |
+
"model.language_model.layers.13.self_attn.k_norm",
|
| 240 |
+
"model.language_model.layers.13.self_attn.q_norm",
|
| 241 |
+
"model.language_model.layers.14.input_layernorm",
|
| 242 |
+
"model.language_model.layers.14.layer_scalar",
|
| 243 |
+
"model.language_model.layers.14.post_attention_layernorm",
|
| 244 |
+
"model.language_model.layers.14.post_feedforward_layernorm",
|
| 245 |
+
"model.language_model.layers.14.pre_feedforward_layernorm",
|
| 246 |
+
"model.language_model.layers.14.self_attn.k_norm",
|
| 247 |
+
"model.language_model.layers.14.self_attn.q_norm",
|
| 248 |
+
"model.language_model.layers.15.input_layernorm",
|
| 249 |
+
"model.language_model.layers.15.layer_scalar",
|
| 250 |
+
"model.language_model.layers.15.post_attention_layernorm",
|
| 251 |
+
"model.language_model.layers.15.post_feedforward_layernorm",
|
| 252 |
+
"model.language_model.layers.15.pre_feedforward_layernorm",
|
| 253 |
+
"model.language_model.layers.15.self_attn.k_norm",
|
| 254 |
+
"model.language_model.layers.15.self_attn.q_norm",
|
| 255 |
+
"model.language_model.layers.16.input_layernorm",
|
| 256 |
+
"model.language_model.layers.16.layer_scalar",
|
| 257 |
+
"model.language_model.layers.16.post_attention_layernorm",
|
| 258 |
+
"model.language_model.layers.16.post_feedforward_layernorm",
|
| 259 |
+
"model.language_model.layers.16.pre_feedforward_layernorm",
|
| 260 |
+
"model.language_model.layers.16.self_attn.k_norm",
|
| 261 |
+
"model.language_model.layers.16.self_attn.q_norm",
|
| 262 |
+
"model.language_model.layers.17.input_layernorm",
|
| 263 |
+
"model.language_model.layers.17.layer_scalar",
|
| 264 |
+
"model.language_model.layers.17.post_attention_layernorm",
|
| 265 |
+
"model.language_model.layers.17.post_feedforward_layernorm",
|
| 266 |
+
"model.language_model.layers.17.pre_feedforward_layernorm",
|
| 267 |
+
"model.language_model.layers.17.self_attn.k_norm",
|
| 268 |
+
"model.language_model.layers.17.self_attn.q_norm",
|
| 269 |
+
"model.language_model.layers.18.input_layernorm",
|
| 270 |
+
"model.language_model.layers.18.layer_scalar",
|
| 271 |
+
"model.language_model.layers.18.post_attention_layernorm",
|
| 272 |
+
"model.language_model.layers.18.post_feedforward_layernorm",
|
| 273 |
+
"model.language_model.layers.18.pre_feedforward_layernorm",
|
| 274 |
+
"model.language_model.layers.18.self_attn.k_norm",
|
| 275 |
+
"model.language_model.layers.18.self_attn.q_norm",
|
| 276 |
+
"model.language_model.layers.19.input_layernorm",
|
| 277 |
+
"model.language_model.layers.19.layer_scalar",
|
| 278 |
+
"model.language_model.layers.19.post_attention_layernorm",
|
| 279 |
+
"model.language_model.layers.19.post_feedforward_layernorm",
|
| 280 |
+
"model.language_model.layers.19.pre_feedforward_layernorm",
|
| 281 |
+
"model.language_model.layers.19.self_attn.k_norm",
|
| 282 |
+
"model.language_model.layers.19.self_attn.q_norm",
|
| 283 |
+
"model.language_model.layers.2.input_layernorm",
|
| 284 |
+
"model.language_model.layers.2.layer_scalar",
|
| 285 |
+
"model.language_model.layers.2.post_attention_layernorm",
|
| 286 |
+
"model.language_model.layers.2.post_feedforward_layernorm",
|
| 287 |
+
"model.language_model.layers.2.pre_feedforward_layernorm",
|
| 288 |
+
"model.language_model.layers.2.self_attn.k_norm",
|
| 289 |
+
"model.language_model.layers.2.self_attn.q_norm",
|
| 290 |
+
"model.language_model.layers.20.input_layernorm",
|
| 291 |
+
"model.language_model.layers.20.layer_scalar",
|
| 292 |
+
"model.language_model.layers.20.post_attention_layernorm",
|
| 293 |
+
"model.language_model.layers.20.post_feedforward_layernorm",
|
| 294 |
+
"model.language_model.layers.20.pre_feedforward_layernorm",
|
| 295 |
+
"model.language_model.layers.20.self_attn.k_norm",
|
| 296 |
+
"model.language_model.layers.20.self_attn.q_norm",
|
| 297 |
+
"model.language_model.layers.21.input_layernorm",
|
| 298 |
+
"model.language_model.layers.21.layer_scalar",
|
| 299 |
+
"model.language_model.layers.21.post_attention_layernorm",
|
| 300 |
+
"model.language_model.layers.21.post_feedforward_layernorm",
|
| 301 |
+
"model.language_model.layers.21.pre_feedforward_layernorm",
|
| 302 |
+
"model.language_model.layers.21.self_attn.k_norm",
|
| 303 |
+
"model.language_model.layers.21.self_attn.q_norm",
|
| 304 |
+
"model.language_model.layers.22.input_layernorm",
|
| 305 |
+
"model.language_model.layers.22.layer_scalar",
|
| 306 |
+
"model.language_model.layers.22.post_attention_layernorm",
|
| 307 |
+
"model.language_model.layers.22.post_feedforward_layernorm",
|
| 308 |
+
"model.language_model.layers.22.pre_feedforward_layernorm",
|
| 309 |
+
"model.language_model.layers.22.self_attn.k_norm",
|
| 310 |
+
"model.language_model.layers.22.self_attn.q_norm",
|
| 311 |
+
"model.language_model.layers.23.input_layernorm",
|
| 312 |
+
"model.language_model.layers.23.layer_scalar",
|
| 313 |
+
"model.language_model.layers.23.post_attention_layernorm",
|
| 314 |
+
"model.language_model.layers.23.post_feedforward_layernorm",
|
| 315 |
+
"model.language_model.layers.23.pre_feedforward_layernorm",
|
| 316 |
+
"model.language_model.layers.23.self_attn.k_norm",
|
| 317 |
+
"model.language_model.layers.23.self_attn.q_norm",
|
| 318 |
+
"model.language_model.layers.24.input_layernorm",
|
| 319 |
+
"model.language_model.layers.24.layer_scalar",
|
| 320 |
+
"model.language_model.layers.24.post_attention_layernorm",
|
| 321 |
+
"model.language_model.layers.24.post_feedforward_layernorm",
|
| 322 |
+
"model.language_model.layers.24.pre_feedforward_layernorm",
|
| 323 |
+
"model.language_model.layers.24.self_attn.k_norm",
|
| 324 |
+
"model.language_model.layers.24.self_attn.q_norm",
|
| 325 |
+
"model.language_model.layers.25.input_layernorm",
|
| 326 |
+
"model.language_model.layers.25.layer_scalar",
|
| 327 |
+
"model.language_model.layers.25.post_attention_layernorm",
|
| 328 |
+
"model.language_model.layers.25.post_feedforward_layernorm",
|
| 329 |
+
"model.language_model.layers.25.pre_feedforward_layernorm",
|
| 330 |
+
"model.language_model.layers.25.self_attn.k_norm",
|
| 331 |
+
"model.language_model.layers.25.self_attn.q_norm",
|
| 332 |
+
"model.language_model.layers.26.input_layernorm",
|
| 333 |
+
"model.language_model.layers.26.layer_scalar",
|
| 334 |
+
"model.language_model.layers.26.post_attention_layernorm",
|
| 335 |
+
"model.language_model.layers.26.post_feedforward_layernorm",
|
| 336 |
+
"model.language_model.layers.26.pre_feedforward_layernorm",
|
| 337 |
+
"model.language_model.layers.26.self_attn.k_norm",
|
| 338 |
+
"model.language_model.layers.26.self_attn.q_norm",
|
| 339 |
+
"model.language_model.layers.27.input_layernorm",
|
| 340 |
+
"model.language_model.layers.27.layer_scalar",
|
| 341 |
+
"model.language_model.layers.27.post_attention_layernorm",
|
| 342 |
+
"model.language_model.layers.27.post_feedforward_layernorm",
|
| 343 |
+
"model.language_model.layers.27.pre_feedforward_layernorm",
|
| 344 |
+
"model.language_model.layers.27.self_attn.k_norm",
|
| 345 |
+
"model.language_model.layers.27.self_attn.q_norm",
|
| 346 |
+
"model.language_model.layers.28.input_layernorm",
|
| 347 |
+
"model.language_model.layers.28.layer_scalar",
|
| 348 |
+
"model.language_model.layers.28.post_attention_layernorm",
|
| 349 |
+
"model.language_model.layers.28.post_feedforward_layernorm",
|
| 350 |
+
"model.language_model.layers.28.pre_feedforward_layernorm",
|
| 351 |
+
"model.language_model.layers.28.self_attn.k_norm",
|
| 352 |
+
"model.language_model.layers.28.self_attn.q_norm",
|
| 353 |
+
"model.language_model.layers.29.input_layernorm",
|
| 354 |
+
"model.language_model.layers.29.layer_scalar",
|
| 355 |
+
"model.language_model.layers.29.post_attention_layernorm",
|
| 356 |
+
"model.language_model.layers.29.post_feedforward_layernorm",
|
| 357 |
+
"model.language_model.layers.29.pre_feedforward_layernorm",
|
| 358 |
+
"model.language_model.layers.29.self_attn.k_norm",
|
| 359 |
+
"model.language_model.layers.29.self_attn.q_norm",
|
| 360 |
+
"model.language_model.layers.3.input_layernorm",
|
| 361 |
+
"model.language_model.layers.3.layer_scalar",
|
| 362 |
+
"model.language_model.layers.3.post_attention_layernorm",
|
| 363 |
+
"model.language_model.layers.3.post_feedforward_layernorm",
|
| 364 |
+
"model.language_model.layers.3.pre_feedforward_layernorm",
|
| 365 |
+
"model.language_model.layers.3.self_attn.k_norm",
|
| 366 |
+
"model.language_model.layers.3.self_attn.q_norm",
|
| 367 |
+
"model.language_model.layers.30.input_layernorm",
|
| 368 |
+
"model.language_model.layers.30.layer_scalar",
|
| 369 |
+
"model.language_model.layers.30.post_attention_layernorm",
|
| 370 |
+
"model.language_model.layers.30.post_feedforward_layernorm",
|
| 371 |
+
"model.language_model.layers.30.pre_feedforward_layernorm",
|
| 372 |
+
"model.language_model.layers.30.self_attn.k_norm",
|
| 373 |
+
"model.language_model.layers.30.self_attn.q_norm",
|
| 374 |
+
"model.language_model.layers.31.input_layernorm",
|
| 375 |
+
"model.language_model.layers.31.layer_scalar",
|
| 376 |
+
"model.language_model.layers.31.post_attention_layernorm",
|
| 377 |
+
"model.language_model.layers.31.post_feedforward_layernorm",
|
| 378 |
+
"model.language_model.layers.31.pre_feedforward_layernorm",
|
| 379 |
+
"model.language_model.layers.31.self_attn.k_norm",
|
| 380 |
+
"model.language_model.layers.31.self_attn.q_norm",
|
| 381 |
+
"model.language_model.layers.32.input_layernorm",
|
| 382 |
+
"model.language_model.layers.32.layer_scalar",
|
| 383 |
+
"model.language_model.layers.32.post_attention_layernorm",
|
| 384 |
+
"model.language_model.layers.32.post_feedforward_layernorm",
|
| 385 |
+
"model.language_model.layers.32.pre_feedforward_layernorm",
|
| 386 |
+
"model.language_model.layers.32.self_attn.k_norm",
|
| 387 |
+
"model.language_model.layers.32.self_attn.q_norm",
|
| 388 |
+
"model.language_model.layers.33.input_layernorm",
|
| 389 |
+
"model.language_model.layers.33.layer_scalar",
|
| 390 |
+
"model.language_model.layers.33.post_attention_layernorm",
|
| 391 |
+
"model.language_model.layers.33.post_feedforward_layernorm",
|
| 392 |
+
"model.language_model.layers.33.pre_feedforward_layernorm",
|
| 393 |
+
"model.language_model.layers.33.self_attn.k_norm",
|
| 394 |
+
"model.language_model.layers.33.self_attn.q_norm",
|
| 395 |
+
"model.language_model.layers.34.input_layernorm",
|
| 396 |
+
"model.language_model.layers.34.layer_scalar",
|
| 397 |
+
"model.language_model.layers.34.post_attention_layernorm",
|
| 398 |
+
"model.language_model.layers.34.post_feedforward_layernorm",
|
| 399 |
+
"model.language_model.layers.34.pre_feedforward_layernorm",
|
| 400 |
+
"model.language_model.layers.34.self_attn.k_norm",
|
| 401 |
+
"model.language_model.layers.34.self_attn.q_norm",
|
| 402 |
+
"model.language_model.layers.35.input_layernorm",
|
| 403 |
+
"model.language_model.layers.35.layer_scalar",
|
| 404 |
+
"model.language_model.layers.35.post_attention_layernorm",
|
| 405 |
+
"model.language_model.layers.35.post_feedforward_layernorm",
|
| 406 |
+
"model.language_model.layers.35.pre_feedforward_layernorm",
|
| 407 |
+
"model.language_model.layers.35.self_attn.k_norm",
|
| 408 |
+
"model.language_model.layers.35.self_attn.q_norm",
|
| 409 |
+
"model.language_model.layers.36.input_layernorm",
|
| 410 |
+
"model.language_model.layers.36.layer_scalar",
|
| 411 |
+
"model.language_model.layers.36.post_attention_layernorm",
|
| 412 |
+
"model.language_model.layers.36.post_feedforward_layernorm",
|
| 413 |
+
"model.language_model.layers.36.pre_feedforward_layernorm",
|
| 414 |
+
"model.language_model.layers.36.self_attn.k_norm",
|
| 415 |
+
"model.language_model.layers.36.self_attn.q_norm",
|
| 416 |
+
"model.language_model.layers.37.input_layernorm",
|
| 417 |
+
"model.language_model.layers.37.layer_scalar",
|
| 418 |
+
"model.language_model.layers.37.post_attention_layernorm",
|
| 419 |
+
"model.language_model.layers.37.post_feedforward_layernorm",
|
| 420 |
+
"model.language_model.layers.37.pre_feedforward_layernorm",
|
| 421 |
+
"model.language_model.layers.37.self_attn.k_norm",
|
| 422 |
+
"model.language_model.layers.37.self_attn.q_norm",
|
| 423 |
+
"model.language_model.layers.38.input_layernorm",
|
| 424 |
+
"model.language_model.layers.38.layer_scalar",
|
| 425 |
+
"model.language_model.layers.38.post_attention_layernorm",
|
| 426 |
+
"model.language_model.layers.38.post_feedforward_layernorm",
|
| 427 |
+
"model.language_model.layers.38.pre_feedforward_layernorm",
|
| 428 |
+
"model.language_model.layers.38.self_attn.k_norm",
|
| 429 |
+
"model.language_model.layers.38.self_attn.q_norm",
|
| 430 |
+
"model.language_model.layers.39.input_layernorm",
|
| 431 |
+
"model.language_model.layers.39.layer_scalar",
|
| 432 |
+
"model.language_model.layers.39.post_attention_layernorm",
|
| 433 |
+
"model.language_model.layers.39.post_feedforward_layernorm",
|
| 434 |
+
"model.language_model.layers.39.pre_feedforward_layernorm",
|
| 435 |
+
"model.language_model.layers.39.self_attn.k_norm",
|
| 436 |
+
"model.language_model.layers.39.self_attn.q_norm",
|
| 437 |
+
"model.language_model.layers.4.input_layernorm",
|
| 438 |
+
"model.language_model.layers.4.layer_scalar",
|
| 439 |
+
"model.language_model.layers.4.post_attention_layernorm",
|
| 440 |
+
"model.language_model.layers.4.post_feedforward_layernorm",
|
| 441 |
+
"model.language_model.layers.4.pre_feedforward_layernorm",
|
| 442 |
+
"model.language_model.layers.4.self_attn.k_norm",
|
| 443 |
+
"model.language_model.layers.4.self_attn.q_norm",
|
| 444 |
+
"model.language_model.layers.40.input_layernorm",
|
| 445 |
+
"model.language_model.layers.40.layer_scalar",
|
| 446 |
+
"model.language_model.layers.40.post_attention_layernorm",
|
| 447 |
+
"model.language_model.layers.40.post_feedforward_layernorm",
|
| 448 |
+
"model.language_model.layers.40.pre_feedforward_layernorm",
|
| 449 |
+
"model.language_model.layers.40.self_attn.k_norm",
|
| 450 |
+
"model.language_model.layers.40.self_attn.q_norm",
|
| 451 |
+
"model.language_model.layers.41.input_layernorm",
|
| 452 |
+
"model.language_model.layers.41.layer_scalar",
|
| 453 |
+
"model.language_model.layers.41.post_attention_layernorm",
|
| 454 |
+
"model.language_model.layers.41.post_feedforward_layernorm",
|
| 455 |
+
"model.language_model.layers.41.pre_feedforward_layernorm",
|
| 456 |
+
"model.language_model.layers.41.self_attn.k_norm",
|
| 457 |
+
"model.language_model.layers.41.self_attn.q_norm",
|
| 458 |
+
"model.language_model.layers.42.input_layernorm",
|
| 459 |
+
"model.language_model.layers.42.layer_scalar",
|
| 460 |
+
"model.language_model.layers.42.post_attention_layernorm",
|
| 461 |
+
"model.language_model.layers.42.post_feedforward_layernorm",
|
| 462 |
+
"model.language_model.layers.42.pre_feedforward_layernorm",
|
| 463 |
+
"model.language_model.layers.42.self_attn.k_norm",
|
| 464 |
+
"model.language_model.layers.42.self_attn.q_norm",
|
| 465 |
+
"model.language_model.layers.43.input_layernorm",
|
| 466 |
+
"model.language_model.layers.43.layer_scalar",
|
| 467 |
+
"model.language_model.layers.43.post_attention_layernorm",
|
| 468 |
+
"model.language_model.layers.43.post_feedforward_layernorm",
|
| 469 |
+
"model.language_model.layers.43.pre_feedforward_layernorm",
|
| 470 |
+
"model.language_model.layers.43.self_attn.k_norm",
|
| 471 |
+
"model.language_model.layers.43.self_attn.q_norm",
|
| 472 |
+
"model.language_model.layers.44.input_layernorm",
|
| 473 |
+
"model.language_model.layers.44.layer_scalar",
|
| 474 |
+
"model.language_model.layers.44.post_attention_layernorm",
|
| 475 |
+
"model.language_model.layers.44.post_feedforward_layernorm",
|
| 476 |
+
"model.language_model.layers.44.pre_feedforward_layernorm",
|
| 477 |
+
"model.language_model.layers.44.self_attn.k_norm",
|
| 478 |
+
"model.language_model.layers.44.self_attn.q_norm",
|
| 479 |
+
"model.language_model.layers.45.input_layernorm",
|
| 480 |
+
"model.language_model.layers.45.layer_scalar",
|
| 481 |
+
"model.language_model.layers.45.post_attention_layernorm",
|
| 482 |
+
"model.language_model.layers.45.post_feedforward_layernorm",
|
| 483 |
+
"model.language_model.layers.45.pre_feedforward_layernorm",
|
| 484 |
+
"model.language_model.layers.45.self_attn.k_norm",
|
| 485 |
+
"model.language_model.layers.45.self_attn.q_norm",
|
| 486 |
+
"model.language_model.layers.46.input_layernorm",
|
| 487 |
+
"model.language_model.layers.46.layer_scalar",
|
| 488 |
+
"model.language_model.layers.46.post_attention_layernorm",
|
| 489 |
+
"model.language_model.layers.46.post_feedforward_layernorm",
|
| 490 |
+
"model.language_model.layers.46.pre_feedforward_layernorm",
|
| 491 |
+
"model.language_model.layers.46.self_attn.k_norm",
|
| 492 |
+
"model.language_model.layers.46.self_attn.q_norm",
|
| 493 |
+
"model.language_model.layers.47.input_layernorm",
|
| 494 |
+
"model.language_model.layers.47.layer_scalar",
|
| 495 |
+
"model.language_model.layers.47.post_attention_layernorm",
|
| 496 |
+
"model.language_model.layers.47.post_feedforward_layernorm",
|
| 497 |
+
"model.language_model.layers.47.pre_feedforward_layernorm",
|
| 498 |
+
"model.language_model.layers.47.self_attn.k_norm",
|
| 499 |
+
"model.language_model.layers.47.self_attn.q_norm",
|
| 500 |
+
"model.language_model.layers.48.input_layernorm",
|
| 501 |
+
"model.language_model.layers.48.layer_scalar",
|
| 502 |
+
"model.language_model.layers.48.post_attention_layernorm",
|
| 503 |
+
"model.language_model.layers.48.post_feedforward_layernorm",
|
| 504 |
+
"model.language_model.layers.48.pre_feedforward_layernorm",
|
| 505 |
+
"model.language_model.layers.48.self_attn.k_norm",
|
| 506 |
+
"model.language_model.layers.48.self_attn.q_norm",
|
| 507 |
+
"model.language_model.layers.49.input_layernorm",
|
| 508 |
+
"model.language_model.layers.49.layer_scalar",
|
| 509 |
+
"model.language_model.layers.49.post_attention_layernorm",
|
| 510 |
+
"model.language_model.layers.49.post_feedforward_layernorm",
|
| 511 |
+
"model.language_model.layers.49.pre_feedforward_layernorm",
|
| 512 |
+
"model.language_model.layers.49.self_attn.k_norm",
|
| 513 |
+
"model.language_model.layers.49.self_attn.q_norm",
|
| 514 |
+
"model.language_model.layers.5.input_layernorm",
|
| 515 |
+
"model.language_model.layers.5.layer_scalar",
|
| 516 |
+
"model.language_model.layers.5.post_attention_layernorm",
|
| 517 |
+
"model.language_model.layers.5.post_feedforward_layernorm",
|
| 518 |
+
"model.language_model.layers.5.pre_feedforward_layernorm",
|
| 519 |
+
"model.language_model.layers.5.self_attn.k_norm",
|
| 520 |
+
"model.language_model.layers.5.self_attn.q_norm",
|
| 521 |
+
"model.language_model.layers.50.input_layernorm",
|
| 522 |
+
"model.language_model.layers.50.layer_scalar",
|
| 523 |
+
"model.language_model.layers.50.post_attention_layernorm",
|
| 524 |
+
"model.language_model.layers.50.post_feedforward_layernorm",
|
| 525 |
+
"model.language_model.layers.50.pre_feedforward_layernorm",
|
| 526 |
+
"model.language_model.layers.50.self_attn.k_norm",
|
| 527 |
+
"model.language_model.layers.50.self_attn.q_norm",
|
| 528 |
+
"model.language_model.layers.51.input_layernorm",
|
| 529 |
+
"model.language_model.layers.51.layer_scalar",
|
| 530 |
+
"model.language_model.layers.51.post_attention_layernorm",
|
| 531 |
+
"model.language_model.layers.51.post_feedforward_layernorm",
|
| 532 |
+
"model.language_model.layers.51.pre_feedforward_layernorm",
|
| 533 |
+
"model.language_model.layers.51.self_attn.k_norm",
|
| 534 |
+
"model.language_model.layers.51.self_attn.q_norm",
|
| 535 |
+
"model.language_model.layers.52.input_layernorm",
|
| 536 |
+
"model.language_model.layers.52.layer_scalar",
|
| 537 |
+
"model.language_model.layers.52.post_attention_layernorm",
|
| 538 |
+
"model.language_model.layers.52.post_feedforward_layernorm",
|
| 539 |
+
"model.language_model.layers.52.pre_feedforward_layernorm",
|
| 540 |
+
"model.language_model.layers.52.self_attn.k_norm",
|
| 541 |
+
"model.language_model.layers.52.self_attn.q_norm",
|
| 542 |
+
"model.language_model.layers.53.input_layernorm",
|
| 543 |
+
"model.language_model.layers.53.layer_scalar",
|
| 544 |
+
"model.language_model.layers.53.post_attention_layernorm",
|
| 545 |
+
"model.language_model.layers.53.post_feedforward_layernorm",
|
| 546 |
+
"model.language_model.layers.53.pre_feedforward_layernorm",
|
| 547 |
+
"model.language_model.layers.53.self_attn.k_norm",
|
| 548 |
+
"model.language_model.layers.53.self_attn.q_norm",
|
| 549 |
+
"model.language_model.layers.54.input_layernorm",
|
| 550 |
+
"model.language_model.layers.54.layer_scalar",
|
| 551 |
+
"model.language_model.layers.54.post_attention_layernorm",
|
| 552 |
+
"model.language_model.layers.54.post_feedforward_layernorm",
|
| 553 |
+
"model.language_model.layers.54.pre_feedforward_layernorm",
|
| 554 |
+
"model.language_model.layers.54.self_attn.k_norm",
|
| 555 |
+
"model.language_model.layers.54.self_attn.q_norm",
|
| 556 |
+
"model.language_model.layers.55.input_layernorm",
|
| 557 |
+
"model.language_model.layers.55.layer_scalar",
|
| 558 |
+
"model.language_model.layers.55.post_attention_layernorm",
|
| 559 |
+
"model.language_model.layers.55.post_feedforward_layernorm",
|
| 560 |
+
"model.language_model.layers.55.pre_feedforward_layernorm",
|
| 561 |
+
"model.language_model.layers.55.self_attn.k_norm",
|
| 562 |
+
"model.language_model.layers.55.self_attn.q_norm",
|
| 563 |
+
"model.language_model.layers.56.input_layernorm",
|
| 564 |
+
"model.language_model.layers.56.layer_scalar",
|
| 565 |
+
"model.language_model.layers.56.post_attention_layernorm",
|
| 566 |
+
"model.language_model.layers.56.post_feedforward_layernorm",
|
| 567 |
+
"model.language_model.layers.56.pre_feedforward_layernorm",
|
| 568 |
+
"model.language_model.layers.56.self_attn.k_norm",
|
| 569 |
+
"model.language_model.layers.56.self_attn.q_norm",
|
| 570 |
+
"model.language_model.layers.57.input_layernorm",
|
| 571 |
+
"model.language_model.layers.57.layer_scalar",
|
| 572 |
+
"model.language_model.layers.57.post_attention_layernorm",
|
| 573 |
+
"model.language_model.layers.57.post_feedforward_layernorm",
|
| 574 |
+
"model.language_model.layers.57.pre_feedforward_layernorm",
|
| 575 |
+
"model.language_model.layers.57.self_attn.k_norm",
|
| 576 |
+
"model.language_model.layers.57.self_attn.q_norm",
|
| 577 |
+
"model.language_model.layers.58.input_layernorm",
|
| 578 |
+
"model.language_model.layers.58.layer_scalar",
|
| 579 |
+
"model.language_model.layers.58.post_attention_layernorm",
|
| 580 |
+
"model.language_model.layers.58.post_feedforward_layernorm",
|
| 581 |
+
"model.language_model.layers.58.pre_feedforward_layernorm",
|
| 582 |
+
"model.language_model.layers.58.self_attn.k_norm",
|
| 583 |
+
"model.language_model.layers.58.self_attn.q_norm",
|
| 584 |
+
"model.language_model.layers.59.input_layernorm",
|
| 585 |
+
"model.language_model.layers.59.layer_scalar",
|
| 586 |
+
"model.language_model.layers.59.post_attention_layernorm",
|
| 587 |
+
"model.language_model.layers.59.post_feedforward_layernorm",
|
| 588 |
+
"model.language_model.layers.59.pre_feedforward_layernorm",
|
| 589 |
+
"model.language_model.layers.59.self_attn.k_norm",
|
| 590 |
+
"model.language_model.layers.59.self_attn.q_norm",
|
| 591 |
+
"model.language_model.layers.6.input_layernorm",
|
| 592 |
+
"model.language_model.layers.6.layer_scalar",
|
| 593 |
+
"model.language_model.layers.6.post_attention_layernorm",
|
| 594 |
+
"model.language_model.layers.6.post_feedforward_layernorm",
|
| 595 |
+
"model.language_model.layers.6.pre_feedforward_layernorm",
|
| 596 |
+
"model.language_model.layers.6.self_attn.k_norm",
|
| 597 |
+
"model.language_model.layers.6.self_attn.q_norm",
|
| 598 |
+
"model.language_model.layers.7.input_layernorm",
|
| 599 |
+
"model.language_model.layers.7.layer_scalar",
|
| 600 |
+
"model.language_model.layers.7.post_attention_layernorm",
|
| 601 |
+
"model.language_model.layers.7.post_feedforward_layernorm",
|
| 602 |
+
"model.language_model.layers.7.pre_feedforward_layernorm",
|
| 603 |
+
"model.language_model.layers.7.self_attn.k_norm",
|
| 604 |
+
"model.language_model.layers.7.self_attn.q_norm",
|
| 605 |
+
"model.language_model.layers.8.input_layernorm",
|
| 606 |
+
"model.language_model.layers.8.layer_scalar",
|
| 607 |
+
"model.language_model.layers.8.post_attention_layernorm",
|
| 608 |
+
"model.language_model.layers.8.post_feedforward_layernorm",
|
| 609 |
+
"model.language_model.layers.8.pre_feedforward_layernorm",
|
| 610 |
+
"model.language_model.layers.8.self_attn.k_norm",
|
| 611 |
+
"model.language_model.layers.8.self_attn.q_norm",
|
| 612 |
+
"model.language_model.layers.9.input_layernorm",
|
| 613 |
+
"model.language_model.layers.9.layer_scalar",
|
| 614 |
+
"model.language_model.layers.9.post_attention_layernorm",
|
| 615 |
+
"model.language_model.layers.9.post_feedforward_layernorm",
|
| 616 |
+
"model.language_model.layers.9.pre_feedforward_layernorm",
|
| 617 |
+
"model.language_model.layers.9.self_attn.k_norm",
|
| 618 |
+
"model.language_model.layers.9.self_attn.q_norm",
|
| 619 |
+
"model.language_model.norm",
|
| 620 |
+
"model.vision_tower.encoder.layers.0.input_layernorm",
|
| 621 |
+
"model.vision_tower.encoder.layers.0.mlp.down_proj.linear",
|
| 622 |
+
"model.vision_tower.encoder.layers.0.mlp.gate_proj.linear",
|
| 623 |
+
"model.vision_tower.encoder.layers.0.mlp.up_proj.linear",
|
| 624 |
+
"model.vision_tower.encoder.layers.0.post_attention_layernorm",
|
| 625 |
+
"model.vision_tower.encoder.layers.0.post_feedforward_layernorm",
|
| 626 |
+
"model.vision_tower.encoder.layers.0.pre_feedforward_layernorm",
|
| 627 |
+
"model.vision_tower.encoder.layers.0.self_attn.k_norm",
|
| 628 |
+
"model.vision_tower.encoder.layers.0.self_attn.k_proj.linear",
|
| 629 |
+
"model.vision_tower.encoder.layers.0.self_attn.o_proj.linear",
|
| 630 |
+
"model.vision_tower.encoder.layers.0.self_attn.q_norm",
|
| 631 |
+
"model.vision_tower.encoder.layers.0.self_attn.q_proj.linear",
|
| 632 |
+
"model.vision_tower.encoder.layers.0.self_attn.v_proj.linear",
|
| 633 |
+
"model.vision_tower.encoder.layers.1.input_layernorm",
|
| 634 |
+
"model.vision_tower.encoder.layers.1.mlp.down_proj.linear",
|
| 635 |
+
"model.vision_tower.encoder.layers.1.mlp.gate_proj.linear",
|
| 636 |
+
"model.vision_tower.encoder.layers.1.mlp.up_proj.linear",
|
| 637 |
+
"model.vision_tower.encoder.layers.1.post_attention_layernorm",
|
| 638 |
+
"model.vision_tower.encoder.layers.1.post_feedforward_layernorm",
|
| 639 |
+
"model.vision_tower.encoder.layers.1.pre_feedforward_layernorm",
|
| 640 |
+
"model.vision_tower.encoder.layers.1.self_attn.k_norm",
|
| 641 |
+
"model.vision_tower.encoder.layers.1.self_attn.k_proj.linear",
|
| 642 |
+
"model.vision_tower.encoder.layers.1.self_attn.o_proj.linear",
|
| 643 |
+
"model.vision_tower.encoder.layers.1.self_attn.q_norm",
|
| 644 |
+
"model.vision_tower.encoder.layers.1.self_attn.q_proj.linear",
|
| 645 |
+
"model.vision_tower.encoder.layers.1.self_attn.v_proj.linear",
|
| 646 |
+
"model.vision_tower.encoder.layers.10.input_layernorm",
|
| 647 |
+
"model.vision_tower.encoder.layers.10.mlp.down_proj.linear",
|
| 648 |
+
"model.vision_tower.encoder.layers.10.mlp.gate_proj.linear",
|
| 649 |
+
"model.vision_tower.encoder.layers.10.mlp.up_proj.linear",
|
| 650 |
+
"model.vision_tower.encoder.layers.10.post_attention_layernorm",
|
| 651 |
+
"model.vision_tower.encoder.layers.10.post_feedforward_layernorm",
|
| 652 |
+
"model.vision_tower.encoder.layers.10.pre_feedforward_layernorm",
|
| 653 |
+
"model.vision_tower.encoder.layers.10.self_attn.k_norm",
|
| 654 |
+
"model.vision_tower.encoder.layers.10.self_attn.k_proj.linear",
|
| 655 |
+
"model.vision_tower.encoder.layers.10.self_attn.o_proj.linear",
|
| 656 |
+
"model.vision_tower.encoder.layers.10.self_attn.q_norm",
|
| 657 |
+
"model.vision_tower.encoder.layers.10.self_attn.q_proj.linear",
|
| 658 |
+
"model.vision_tower.encoder.layers.10.self_attn.v_proj.linear",
|
| 659 |
+
"model.vision_tower.encoder.layers.11.input_layernorm",
|
| 660 |
+
"model.vision_tower.encoder.layers.11.mlp.down_proj.linear",
|
| 661 |
+
"model.vision_tower.encoder.layers.11.mlp.gate_proj.linear",
|
| 662 |
+
"model.vision_tower.encoder.layers.11.mlp.up_proj.linear",
|
| 663 |
+
"model.vision_tower.encoder.layers.11.post_attention_layernorm",
|
| 664 |
+
"model.vision_tower.encoder.layers.11.post_feedforward_layernorm",
|
| 665 |
+
"model.vision_tower.encoder.layers.11.pre_feedforward_layernorm",
|
| 666 |
+
"model.vision_tower.encoder.layers.11.self_attn.k_norm",
|
| 667 |
+
"model.vision_tower.encoder.layers.11.self_attn.k_proj.linear",
|
| 668 |
+
"model.vision_tower.encoder.layers.11.self_attn.o_proj.linear",
|
| 669 |
+
"model.vision_tower.encoder.layers.11.self_attn.q_norm",
|
| 670 |
+
"model.vision_tower.encoder.layers.11.self_attn.q_proj.linear",
|
| 671 |
+
"model.vision_tower.encoder.layers.11.self_attn.v_proj.linear",
|
| 672 |
+
"model.vision_tower.encoder.layers.12.input_layernorm",
|
| 673 |
+
"model.vision_tower.encoder.layers.12.mlp.down_proj.linear",
|
| 674 |
+
"model.vision_tower.encoder.layers.12.mlp.gate_proj.linear",
|
| 675 |
+
"model.vision_tower.encoder.layers.12.mlp.up_proj.linear",
|
| 676 |
+
"model.vision_tower.encoder.layers.12.post_attention_layernorm",
|
| 677 |
+
"model.vision_tower.encoder.layers.12.post_feedforward_layernorm",
|
| 678 |
+
"model.vision_tower.encoder.layers.12.pre_feedforward_layernorm",
|
| 679 |
+
"model.vision_tower.encoder.layers.12.self_attn.k_norm",
|
| 680 |
+
"model.vision_tower.encoder.layers.12.self_attn.k_proj.linear",
|
| 681 |
+
"model.vision_tower.encoder.layers.12.self_attn.o_proj.linear",
|
| 682 |
+
"model.vision_tower.encoder.layers.12.self_attn.q_norm",
|
| 683 |
+
"model.vision_tower.encoder.layers.12.self_attn.q_proj.linear",
|
| 684 |
+
"model.vision_tower.encoder.layers.12.self_attn.v_proj.linear",
|
| 685 |
+
"model.vision_tower.encoder.layers.13.input_layernorm",
|
| 686 |
+
"model.vision_tower.encoder.layers.13.mlp.down_proj.linear",
|
| 687 |
+
"model.vision_tower.encoder.layers.13.mlp.gate_proj.linear",
|
| 688 |
+
"model.vision_tower.encoder.layers.13.mlp.up_proj.linear",
|
| 689 |
+
"model.vision_tower.encoder.layers.13.post_attention_layernorm",
|
| 690 |
+
"model.vision_tower.encoder.layers.13.post_feedforward_layernorm",
|
| 691 |
+
"model.vision_tower.encoder.layers.13.pre_feedforward_layernorm",
|
| 692 |
+
"model.vision_tower.encoder.layers.13.self_attn.k_norm",
|
| 693 |
+
"model.vision_tower.encoder.layers.13.self_attn.k_proj.linear",
|
| 694 |
+
"model.vision_tower.encoder.layers.13.self_attn.o_proj.linear",
|
| 695 |
+
"model.vision_tower.encoder.layers.13.self_attn.q_norm",
|
| 696 |
+
"model.vision_tower.encoder.layers.13.self_attn.q_proj.linear",
|
| 697 |
+
"model.vision_tower.encoder.layers.13.self_attn.v_proj.linear",
|
| 698 |
+
"model.vision_tower.encoder.layers.14.input_layernorm",
|
| 699 |
+
"model.vision_tower.encoder.layers.14.mlp.down_proj.linear",
|
| 700 |
+
"model.vision_tower.encoder.layers.14.mlp.gate_proj.linear",
|
| 701 |
+
"model.vision_tower.encoder.layers.14.mlp.up_proj.linear",
|
| 702 |
+
"model.vision_tower.encoder.layers.14.post_attention_layernorm",
|
| 703 |
+
"model.vision_tower.encoder.layers.14.post_feedforward_layernorm",
|
| 704 |
+
"model.vision_tower.encoder.layers.14.pre_feedforward_layernorm",
|
| 705 |
+
"model.vision_tower.encoder.layers.14.self_attn.k_norm",
|
| 706 |
+
"model.vision_tower.encoder.layers.14.self_attn.k_proj.linear",
|
| 707 |
+
"model.vision_tower.encoder.layers.14.self_attn.o_proj.linear",
|
| 708 |
+
"model.vision_tower.encoder.layers.14.self_attn.q_norm",
|
| 709 |
+
"model.vision_tower.encoder.layers.14.self_attn.q_proj.linear",
|
| 710 |
+
"model.vision_tower.encoder.layers.14.self_attn.v_proj.linear",
|
| 711 |
+
"model.vision_tower.encoder.layers.15.input_layernorm",
|
| 712 |
+
"model.vision_tower.encoder.layers.15.mlp.down_proj.linear",
|
| 713 |
+
"model.vision_tower.encoder.layers.15.mlp.gate_proj.linear",
|
| 714 |
+
"model.vision_tower.encoder.layers.15.mlp.up_proj.linear",
|
| 715 |
+
"model.vision_tower.encoder.layers.15.post_attention_layernorm",
|
| 716 |
+
"model.vision_tower.encoder.layers.15.post_feedforward_layernorm",
|
| 717 |
+
"model.vision_tower.encoder.layers.15.pre_feedforward_layernorm",
|
| 718 |
+
"model.vision_tower.encoder.layers.15.self_attn.k_norm",
|
| 719 |
+
"model.vision_tower.encoder.layers.15.self_attn.k_proj.linear",
|
| 720 |
+
"model.vision_tower.encoder.layers.15.self_attn.o_proj.linear",
|
| 721 |
+
"model.vision_tower.encoder.layers.15.self_attn.q_norm",
|
| 722 |
+
"model.vision_tower.encoder.layers.15.self_attn.q_proj.linear",
|
| 723 |
+
"model.vision_tower.encoder.layers.15.self_attn.v_proj.linear",
|
| 724 |
+
"model.vision_tower.encoder.layers.16.input_layernorm",
|
| 725 |
+
"model.vision_tower.encoder.layers.16.mlp.down_proj.linear",
|
| 726 |
+
"model.vision_tower.encoder.layers.16.mlp.gate_proj.linear",
|
| 727 |
+
"model.vision_tower.encoder.layers.16.mlp.up_proj.linear",
|
| 728 |
+
"model.vision_tower.encoder.layers.16.post_attention_layernorm",
|
| 729 |
+
"model.vision_tower.encoder.layers.16.post_feedforward_layernorm",
|
| 730 |
+
"model.vision_tower.encoder.layers.16.pre_feedforward_layernorm",
|
| 731 |
+
"model.vision_tower.encoder.layers.16.self_attn.k_norm",
|
| 732 |
+
"model.vision_tower.encoder.layers.16.self_attn.k_proj.linear",
|
| 733 |
+
"model.vision_tower.encoder.layers.16.self_attn.o_proj.linear",
|
| 734 |
+
"model.vision_tower.encoder.layers.16.self_attn.q_norm",
|
| 735 |
+
"model.vision_tower.encoder.layers.16.self_attn.q_proj.linear",
|
| 736 |
+
"model.vision_tower.encoder.layers.16.self_attn.v_proj.linear",
|
| 737 |
+
"model.vision_tower.encoder.layers.17.input_layernorm",
|
| 738 |
+
"model.vision_tower.encoder.layers.17.mlp.down_proj.linear",
|
| 739 |
+
"model.vision_tower.encoder.layers.17.mlp.gate_proj.linear",
|
| 740 |
+
"model.vision_tower.encoder.layers.17.mlp.up_proj.linear",
|
| 741 |
+
"model.vision_tower.encoder.layers.17.post_attention_layernorm",
|
| 742 |
+
"model.vision_tower.encoder.layers.17.post_feedforward_layernorm",
|
| 743 |
+
"model.vision_tower.encoder.layers.17.pre_feedforward_layernorm",
|
| 744 |
+
"model.vision_tower.encoder.layers.17.self_attn.k_norm",
|
| 745 |
+
"model.vision_tower.encoder.layers.17.self_attn.k_proj.linear",
|
| 746 |
+
"model.vision_tower.encoder.layers.17.self_attn.o_proj.linear",
|
| 747 |
+
"model.vision_tower.encoder.layers.17.self_attn.q_norm",
|
| 748 |
+
"model.vision_tower.encoder.layers.17.self_attn.q_proj.linear",
|
| 749 |
+
"model.vision_tower.encoder.layers.17.self_attn.v_proj.linear",
|
| 750 |
+
"model.vision_tower.encoder.layers.18.input_layernorm",
|
| 751 |
+
"model.vision_tower.encoder.layers.18.mlp.down_proj.linear",
|
| 752 |
+
"model.vision_tower.encoder.layers.18.mlp.gate_proj.linear",
|
| 753 |
+
"model.vision_tower.encoder.layers.18.mlp.up_proj.linear",
|
| 754 |
+
"model.vision_tower.encoder.layers.18.post_attention_layernorm",
|
| 755 |
+
"model.vision_tower.encoder.layers.18.post_feedforward_layernorm",
|
| 756 |
+
"model.vision_tower.encoder.layers.18.pre_feedforward_layernorm",
|
| 757 |
+
"model.vision_tower.encoder.layers.18.self_attn.k_norm",
|
| 758 |
+
"model.vision_tower.encoder.layers.18.self_attn.k_proj.linear",
|
| 759 |
+
"model.vision_tower.encoder.layers.18.self_attn.o_proj.linear",
|
| 760 |
+
"model.vision_tower.encoder.layers.18.self_attn.q_norm",
|
| 761 |
+
"model.vision_tower.encoder.layers.18.self_attn.q_proj.linear",
|
| 762 |
+
"model.vision_tower.encoder.layers.18.self_attn.v_proj.linear",
|
| 763 |
+
"model.vision_tower.encoder.layers.19.input_layernorm",
|
| 764 |
+
"model.vision_tower.encoder.layers.19.mlp.down_proj.linear",
|
| 765 |
+
"model.vision_tower.encoder.layers.19.mlp.gate_proj.linear",
|
| 766 |
+
"model.vision_tower.encoder.layers.19.mlp.up_proj.linear",
|
| 767 |
+
"model.vision_tower.encoder.layers.19.post_attention_layernorm",
|
| 768 |
+
"model.vision_tower.encoder.layers.19.post_feedforward_layernorm",
|
| 769 |
+
"model.vision_tower.encoder.layers.19.pre_feedforward_layernorm",
|
| 770 |
+
"model.vision_tower.encoder.layers.19.self_attn.k_norm",
|
| 771 |
+
"model.vision_tower.encoder.layers.19.self_attn.k_proj.linear",
|
| 772 |
+
"model.vision_tower.encoder.layers.19.self_attn.o_proj.linear",
|
| 773 |
+
"model.vision_tower.encoder.layers.19.self_attn.q_norm",
|
| 774 |
+
"model.vision_tower.encoder.layers.19.self_attn.q_proj.linear",
|
| 775 |
+
"model.vision_tower.encoder.layers.19.self_attn.v_proj.linear",
|
| 776 |
+
"model.vision_tower.encoder.layers.2.input_layernorm",
|
| 777 |
+
"model.vision_tower.encoder.layers.2.mlp.down_proj.linear",
|
| 778 |
+
"model.vision_tower.encoder.layers.2.mlp.gate_proj.linear",
|
| 779 |
+
"model.vision_tower.encoder.layers.2.mlp.up_proj.linear",
|
| 780 |
+
"model.vision_tower.encoder.layers.2.post_attention_layernorm",
|
| 781 |
+
"model.vision_tower.encoder.layers.2.post_feedforward_layernorm",
|
| 782 |
+
"model.vision_tower.encoder.layers.2.pre_feedforward_layernorm",
|
| 783 |
+
"model.vision_tower.encoder.layers.2.self_attn.k_norm",
|
| 784 |
+
"model.vision_tower.encoder.layers.2.self_attn.k_proj.linear",
|
| 785 |
+
"model.vision_tower.encoder.layers.2.self_attn.o_proj.linear",
|
| 786 |
+
"model.vision_tower.encoder.layers.2.self_attn.q_norm",
|
| 787 |
+
"model.vision_tower.encoder.layers.2.self_attn.q_proj.linear",
|
| 788 |
+
"model.vision_tower.encoder.layers.2.self_attn.v_proj.linear",
|
| 789 |
+
"model.vision_tower.encoder.layers.20.input_layernorm",
|
| 790 |
+
"model.vision_tower.encoder.layers.20.mlp.down_proj.linear",
|
| 791 |
+
"model.vision_tower.encoder.layers.20.mlp.gate_proj.linear",
|
| 792 |
+
"model.vision_tower.encoder.layers.20.mlp.up_proj.linear",
|
| 793 |
+
"model.vision_tower.encoder.layers.20.post_attention_layernorm",
|
| 794 |
+
"model.vision_tower.encoder.layers.20.post_feedforward_layernorm",
|
| 795 |
+
"model.vision_tower.encoder.layers.20.pre_feedforward_layernorm",
|
| 796 |
+
"model.vision_tower.encoder.layers.20.self_attn.k_norm",
|
| 797 |
+
"model.vision_tower.encoder.layers.20.self_attn.k_proj.linear",
|
| 798 |
+
"model.vision_tower.encoder.layers.20.self_attn.o_proj.linear",
|
| 799 |
+
"model.vision_tower.encoder.layers.20.self_attn.q_norm",
|
| 800 |
+
"model.vision_tower.encoder.layers.20.self_attn.q_proj.linear",
|
| 801 |
+
"model.vision_tower.encoder.layers.20.self_attn.v_proj.linear",
|
| 802 |
+
"model.vision_tower.encoder.layers.21.input_layernorm",
|
| 803 |
+
"model.vision_tower.encoder.layers.21.mlp.down_proj.linear",
|
| 804 |
+
"model.vision_tower.encoder.layers.21.mlp.gate_proj.linear",
|
| 805 |
+
"model.vision_tower.encoder.layers.21.mlp.up_proj.linear",
|
| 806 |
+
"model.vision_tower.encoder.layers.21.post_attention_layernorm",
|
| 807 |
+
"model.vision_tower.encoder.layers.21.post_feedforward_layernorm",
|
| 808 |
+
"model.vision_tower.encoder.layers.21.pre_feedforward_layernorm",
|
| 809 |
+
"model.vision_tower.encoder.layers.21.self_attn.k_norm",
|
| 810 |
+
"model.vision_tower.encoder.layers.21.self_attn.k_proj.linear",
|
| 811 |
+
"model.vision_tower.encoder.layers.21.self_attn.o_proj.linear",
|
| 812 |
+
"model.vision_tower.encoder.layers.21.self_attn.q_norm",
|
| 813 |
+
"model.vision_tower.encoder.layers.21.self_attn.q_proj.linear",
|
| 814 |
+
"model.vision_tower.encoder.layers.21.self_attn.v_proj.linear",
|
| 815 |
+
"model.vision_tower.encoder.layers.22.input_layernorm",
|
| 816 |
+
"model.vision_tower.encoder.layers.22.mlp.down_proj.linear",
|
| 817 |
+
"model.vision_tower.encoder.layers.22.mlp.gate_proj.linear",
|
| 818 |
+
"model.vision_tower.encoder.layers.22.mlp.up_proj.linear",
|
| 819 |
+
"model.vision_tower.encoder.layers.22.post_attention_layernorm",
|
| 820 |
+
"model.vision_tower.encoder.layers.22.post_feedforward_layernorm",
|
| 821 |
+
"model.vision_tower.encoder.layers.22.pre_feedforward_layernorm",
|
| 822 |
+
"model.vision_tower.encoder.layers.22.self_attn.k_norm",
|
| 823 |
+
"model.vision_tower.encoder.layers.22.self_attn.k_proj.linear",
|
| 824 |
+
"model.vision_tower.encoder.layers.22.self_attn.o_proj.linear",
|
| 825 |
+
"model.vision_tower.encoder.layers.22.self_attn.q_norm",
|
| 826 |
+
"model.vision_tower.encoder.layers.22.self_attn.q_proj.linear",
|
| 827 |
+
"model.vision_tower.encoder.layers.22.self_attn.v_proj.linear",
|
| 828 |
+
"model.vision_tower.encoder.layers.23.input_layernorm",
|
| 829 |
+
"model.vision_tower.encoder.layers.23.mlp.down_proj.linear",
|
| 830 |
+
"model.vision_tower.encoder.layers.23.mlp.gate_proj.linear",
|
| 831 |
+
"model.vision_tower.encoder.layers.23.mlp.up_proj.linear",
|
| 832 |
+
"model.vision_tower.encoder.layers.23.post_attention_layernorm",
|
| 833 |
+
"model.vision_tower.encoder.layers.23.post_feedforward_layernorm",
|
| 834 |
+
"model.vision_tower.encoder.layers.23.pre_feedforward_layernorm",
|
| 835 |
+
"model.vision_tower.encoder.layers.23.self_attn.k_norm",
|
| 836 |
+
"model.vision_tower.encoder.layers.23.self_attn.k_proj.linear",
|
| 837 |
+
"model.vision_tower.encoder.layers.23.self_attn.o_proj.linear",
|
| 838 |
+
"model.vision_tower.encoder.layers.23.self_attn.q_norm",
|
| 839 |
+
"model.vision_tower.encoder.layers.23.self_attn.q_proj.linear",
|
| 840 |
+
"model.vision_tower.encoder.layers.23.self_attn.v_proj.linear",
|
| 841 |
+
"model.vision_tower.encoder.layers.24.input_layernorm",
|
| 842 |
+
"model.vision_tower.encoder.layers.24.mlp.down_proj.linear",
|
| 843 |
+
"model.vision_tower.encoder.layers.24.mlp.gate_proj.linear",
|
| 844 |
+
"model.vision_tower.encoder.layers.24.mlp.up_proj.linear",
|
| 845 |
+
"model.vision_tower.encoder.layers.24.post_attention_layernorm",
|
| 846 |
+
"model.vision_tower.encoder.layers.24.post_feedforward_layernorm",
|
| 847 |
+
"model.vision_tower.encoder.layers.24.pre_feedforward_layernorm",
|
| 848 |
+
"model.vision_tower.encoder.layers.24.self_attn.k_norm",
|
| 849 |
+
"model.vision_tower.encoder.layers.24.self_attn.k_proj.linear",
|
| 850 |
+
"model.vision_tower.encoder.layers.24.self_attn.o_proj.linear",
|
| 851 |
+
"model.vision_tower.encoder.layers.24.self_attn.q_norm",
|
| 852 |
+
"model.vision_tower.encoder.layers.24.self_attn.q_proj.linear",
|
| 853 |
+
"model.vision_tower.encoder.layers.24.self_attn.v_proj.linear",
|
| 854 |
+
"model.vision_tower.encoder.layers.25.input_layernorm",
|
| 855 |
+
"model.vision_tower.encoder.layers.25.mlp.down_proj.linear",
|
| 856 |
+
"model.vision_tower.encoder.layers.25.mlp.gate_proj.linear",
|
| 857 |
+
"model.vision_tower.encoder.layers.25.mlp.up_proj.linear",
|
| 858 |
+
"model.vision_tower.encoder.layers.25.post_attention_layernorm",
|
| 859 |
+
"model.vision_tower.encoder.layers.25.post_feedforward_layernorm",
|
| 860 |
+
"model.vision_tower.encoder.layers.25.pre_feedforward_layernorm",
|
| 861 |
+
"model.vision_tower.encoder.layers.25.self_attn.k_norm",
|
| 862 |
+
"model.vision_tower.encoder.layers.25.self_attn.k_proj.linear",
|
| 863 |
+
"model.vision_tower.encoder.layers.25.self_attn.o_proj.linear",
|
| 864 |
+
"model.vision_tower.encoder.layers.25.self_attn.q_norm",
|
| 865 |
+
"model.vision_tower.encoder.layers.25.self_attn.q_proj.linear",
|
| 866 |
+
"model.vision_tower.encoder.layers.25.self_attn.v_proj.linear",
|
| 867 |
+
"model.vision_tower.encoder.layers.26.input_layernorm",
|
| 868 |
+
"model.vision_tower.encoder.layers.26.mlp.down_proj.linear",
|
| 869 |
+
"model.vision_tower.encoder.layers.26.mlp.gate_proj.linear",
|
| 870 |
+
"model.vision_tower.encoder.layers.26.mlp.up_proj.linear",
|
| 871 |
+
"model.vision_tower.encoder.layers.26.post_attention_layernorm",
|
| 872 |
+
"model.vision_tower.encoder.layers.26.post_feedforward_layernorm",
|
| 873 |
+
"model.vision_tower.encoder.layers.26.pre_feedforward_layernorm",
|
| 874 |
+
"model.vision_tower.encoder.layers.26.self_attn.k_norm",
|
| 875 |
+
"model.vision_tower.encoder.layers.26.self_attn.k_proj.linear",
|
| 876 |
+
"model.vision_tower.encoder.layers.26.self_attn.o_proj.linear",
|
| 877 |
+
"model.vision_tower.encoder.layers.26.self_attn.q_norm",
|
| 878 |
+
"model.vision_tower.encoder.layers.26.self_attn.q_proj.linear",
|
| 879 |
+
"model.vision_tower.encoder.layers.26.self_attn.v_proj.linear",
|
| 880 |
+
"model.vision_tower.encoder.layers.3.input_layernorm",
|
| 881 |
+
"model.vision_tower.encoder.layers.3.mlp.down_proj.linear",
|
| 882 |
+
"model.vision_tower.encoder.layers.3.mlp.gate_proj.linear",
|
| 883 |
+
"model.vision_tower.encoder.layers.3.mlp.up_proj.linear",
|
| 884 |
+
"model.vision_tower.encoder.layers.3.post_attention_layernorm",
|
| 885 |
+
"model.vision_tower.encoder.layers.3.post_feedforward_layernorm",
|
| 886 |
+
"model.vision_tower.encoder.layers.3.pre_feedforward_layernorm",
|
| 887 |
+
"model.vision_tower.encoder.layers.3.self_attn.k_norm",
|
| 888 |
+
"model.vision_tower.encoder.layers.3.self_attn.k_proj.linear",
|
| 889 |
+
"model.vision_tower.encoder.layers.3.self_attn.o_proj.linear",
|
| 890 |
+
"model.vision_tower.encoder.layers.3.self_attn.q_norm",
|
| 891 |
+
"model.vision_tower.encoder.layers.3.self_attn.q_proj.linear",
|
| 892 |
+
"model.vision_tower.encoder.layers.3.self_attn.v_proj.linear",
|
| 893 |
+
"model.vision_tower.encoder.layers.4.input_layernorm",
|
| 894 |
+
"model.vision_tower.encoder.layers.4.mlp.down_proj.linear",
|
| 895 |
+
"model.vision_tower.encoder.layers.4.mlp.gate_proj.linear",
|
| 896 |
+
"model.vision_tower.encoder.layers.4.mlp.up_proj.linear",
|
| 897 |
+
"model.vision_tower.encoder.layers.4.post_attention_layernorm",
|
| 898 |
+
"model.vision_tower.encoder.layers.4.post_feedforward_layernorm",
|
| 899 |
+
"model.vision_tower.encoder.layers.4.pre_feedforward_layernorm",
|
| 900 |
+
"model.vision_tower.encoder.layers.4.self_attn.k_norm",
|
| 901 |
+
"model.vision_tower.encoder.layers.4.self_attn.k_proj.linear",
|
| 902 |
+
"model.vision_tower.encoder.layers.4.self_attn.o_proj.linear",
|
| 903 |
+
"model.vision_tower.encoder.layers.4.self_attn.q_norm",
|
| 904 |
+
"model.vision_tower.encoder.layers.4.self_attn.q_proj.linear",
|
| 905 |
+
"model.vision_tower.encoder.layers.4.self_attn.v_proj.linear",
|
| 906 |
+
"model.vision_tower.encoder.layers.5.input_layernorm",
|
| 907 |
+
"model.vision_tower.encoder.layers.5.mlp.down_proj.linear",
|
| 908 |
+
"model.vision_tower.encoder.layers.5.mlp.gate_proj.linear",
|
| 909 |
+
"model.vision_tower.encoder.layers.5.mlp.up_proj.linear",
|
| 910 |
+
"model.vision_tower.encoder.layers.5.post_attention_layernorm",
|
| 911 |
+
"model.vision_tower.encoder.layers.5.post_feedforward_layernorm",
|
| 912 |
+
"model.vision_tower.encoder.layers.5.pre_feedforward_layernorm",
|
| 913 |
+
"model.vision_tower.encoder.layers.5.self_attn.k_norm",
|
| 914 |
+
"model.vision_tower.encoder.layers.5.self_attn.k_proj.linear",
|
| 915 |
+
"model.vision_tower.encoder.layers.5.self_attn.o_proj.linear",
|
| 916 |
+
"model.vision_tower.encoder.layers.5.self_attn.q_norm",
|
| 917 |
+
"model.vision_tower.encoder.layers.5.self_attn.q_proj.linear",
|
| 918 |
+
"model.vision_tower.encoder.layers.5.self_attn.v_proj.linear",
|
| 919 |
+
"model.vision_tower.encoder.layers.6.input_layernorm",
|
| 920 |
+
"model.vision_tower.encoder.layers.6.mlp.down_proj.linear",
|
| 921 |
+
"model.vision_tower.encoder.layers.6.mlp.gate_proj.linear",
|
| 922 |
+
"model.vision_tower.encoder.layers.6.mlp.up_proj.linear",
|
| 923 |
+
"model.vision_tower.encoder.layers.6.post_attention_layernorm",
|
| 924 |
+
"model.vision_tower.encoder.layers.6.post_feedforward_layernorm",
|
| 925 |
+
"model.vision_tower.encoder.layers.6.pre_feedforward_layernorm",
|
| 926 |
+
"model.vision_tower.encoder.layers.6.self_attn.k_norm",
|
| 927 |
+
"model.vision_tower.encoder.layers.6.self_attn.k_proj.linear",
|
| 928 |
+
"model.vision_tower.encoder.layers.6.self_attn.o_proj.linear",
|
| 929 |
+
"model.vision_tower.encoder.layers.6.self_attn.q_norm",
|
| 930 |
+
"model.vision_tower.encoder.layers.6.self_attn.q_proj.linear",
|
| 931 |
+
"model.vision_tower.encoder.layers.6.self_attn.v_proj.linear",
|
| 932 |
+
"model.vision_tower.encoder.layers.7.input_layernorm",
|
| 933 |
+
"model.vision_tower.encoder.layers.7.mlp.down_proj.linear",
|
| 934 |
+
"model.vision_tower.encoder.layers.7.mlp.gate_proj.linear",
|
| 935 |
+
"model.vision_tower.encoder.layers.7.mlp.up_proj.linear",
|
| 936 |
+
"model.vision_tower.encoder.layers.7.post_attention_layernorm",
|
| 937 |
+
"model.vision_tower.encoder.layers.7.post_feedforward_layernorm",
|
| 938 |
+
"model.vision_tower.encoder.layers.7.pre_feedforward_layernorm",
|
| 939 |
+
"model.vision_tower.encoder.layers.7.self_attn.k_norm",
|
| 940 |
+
"model.vision_tower.encoder.layers.7.self_attn.k_proj.linear",
|
| 941 |
+
"model.vision_tower.encoder.layers.7.self_attn.o_proj.linear",
|
| 942 |
+
"model.vision_tower.encoder.layers.7.self_attn.q_norm",
|
| 943 |
+
"model.vision_tower.encoder.layers.7.self_attn.q_proj.linear",
|
| 944 |
+
"model.vision_tower.encoder.layers.7.self_attn.v_proj.linear",
|
| 945 |
+
"model.vision_tower.encoder.layers.8.input_layernorm",
|
| 946 |
+
"model.vision_tower.encoder.layers.8.mlp.down_proj.linear",
|
| 947 |
+
"model.vision_tower.encoder.layers.8.mlp.gate_proj.linear",
|
| 948 |
+
"model.vision_tower.encoder.layers.8.mlp.up_proj.linear",
|
| 949 |
+
"model.vision_tower.encoder.layers.8.post_attention_layernorm",
|
| 950 |
+
"model.vision_tower.encoder.layers.8.post_feedforward_layernorm",
|
| 951 |
+
"model.vision_tower.encoder.layers.8.pre_feedforward_layernorm",
|
| 952 |
+
"model.vision_tower.encoder.layers.8.self_attn.k_norm",
|
| 953 |
+
"model.vision_tower.encoder.layers.8.self_attn.k_proj.linear",
|
| 954 |
+
"model.vision_tower.encoder.layers.8.self_attn.o_proj.linear",
|
| 955 |
+
"model.vision_tower.encoder.layers.8.self_attn.q_norm",
|
| 956 |
+
"model.vision_tower.encoder.layers.8.self_attn.q_proj.linear",
|
| 957 |
+
"model.vision_tower.encoder.layers.8.self_attn.v_proj.linear",
|
| 958 |
+
"model.vision_tower.encoder.layers.9.input_layernorm",
|
| 959 |
+
"model.vision_tower.encoder.layers.9.mlp.down_proj.linear",
|
| 960 |
+
"model.vision_tower.encoder.layers.9.mlp.gate_proj.linear",
|
| 961 |
+
"model.vision_tower.encoder.layers.9.mlp.up_proj.linear",
|
| 962 |
+
"model.vision_tower.encoder.layers.9.post_attention_layernorm",
|
| 963 |
+
"model.vision_tower.encoder.layers.9.post_feedforward_layernorm",
|
| 964 |
+
"model.vision_tower.encoder.layers.9.pre_feedforward_layernorm",
|
| 965 |
+
"model.vision_tower.encoder.layers.9.self_attn.k_norm",
|
| 966 |
+
"model.vision_tower.encoder.layers.9.self_attn.k_proj.linear",
|
| 967 |
+
"model.vision_tower.encoder.layers.9.self_attn.o_proj.linear",
|
| 968 |
+
"model.vision_tower.encoder.layers.9.self_attn.q_norm",
|
| 969 |
+
"model.vision_tower.encoder.layers.9.self_attn.q_proj.linear",
|
| 970 |
+
"model.vision_tower.encoder.layers.9.self_attn.v_proj.linear",
|
| 971 |
+
"model.vision_tower.patch_embedder.input_proj",
|
| 972 |
+
"model.vision_tower.patch_embedder.position_embedding_table",
|
| 973 |
+
"model.vision_tower.std_bias",
|
| 974 |
+
"model.vision_tower.std_scale"
|
| 975 |
+
],
|
| 976 |
+
"kv_cache_scheme": null
|
| 977 |
+
}
|
| 978 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106,
|
| 7 |
+
50
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"temperature": 0.9,
|
| 11 |
+
"top_k": 0,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "5.8.0"
|
| 14 |
+
}
|
merge_scale_info.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Base Scale (alpha/r or RS-LoRA): 2.0
|
| 2 |
+
Multiplier Applied: 1.0
|
| 3 |
+
Final Merge Scale: 2.0
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc4b8cb8d5e655139446e87ff1982a8132e2eb6c61531c01942a0c8c55584b6
|
| 3 |
+
size 26391764282
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab85fb85922268d968830f45335ebf5f723db0ff4f717a34ecb94fb5334b3155
|
| 3 |
+
size 6884813798
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 7 |
+
"feature_size": 128,
|
| 8 |
+
"fft_length": 512,
|
| 9 |
+
"fft_overdrive": false,
|
| 10 |
+
"frame_length": 320,
|
| 11 |
+
"hop_length": 160,
|
| 12 |
+
"input_scale_factor": 1.0,
|
| 13 |
+
"max_frequency": 8000.0,
|
| 14 |
+
"mel_floor": 0.001,
|
| 15 |
+
"min_frequency": 0.0,
|
| 16 |
+
"padding_side": "right",
|
| 17 |
+
"padding_value": 0.0,
|
| 18 |
+
"per_bin_mean": null,
|
| 19 |
+
"per_bin_stddev": null,
|
| 20 |
+
"preemphasis": 0.0,
|
| 21 |
+
"preemphasis_htk_flavor": true,
|
| 22 |
+
"return_attention_mask": true,
|
| 23 |
+
"sampling_rate": 16000
|
| 24 |
+
},
|
| 25 |
+
"image_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": false,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"do_resize": true,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0
|
| 34 |
+
],
|
| 35 |
+
"image_processor_type": "Gemma4ImageProcessor",
|
| 36 |
+
"image_seq_length": 280,
|
| 37 |
+
"image_std": [
|
| 38 |
+
1.0,
|
| 39 |
+
1.0,
|
| 40 |
+
1.0
|
| 41 |
+
],
|
| 42 |
+
"max_soft_tokens": 280,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pooling_kernel_size": 3,
|
| 45 |
+
"resample": 3,
|
| 46 |
+
"rescale_factor": 0.00392156862745098
|
| 47 |
+
},
|
| 48 |
+
"image_seq_length": 280,
|
| 49 |
+
"processor_class": "Gemma4Processor",
|
| 50 |
+
"video_processor": {
|
| 51 |
+
"do_convert_rgb": true,
|
| 52 |
+
"do_normalize": true,
|
| 53 |
+
"do_rescale": true,
|
| 54 |
+
"do_resize": true,
|
| 55 |
+
"do_sample_frames": true,
|
| 56 |
+
"image_mean": [
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0
|
| 60 |
+
],
|
| 61 |
+
"image_std": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"max_soft_tokens": 70,
|
| 67 |
+
"num_frames": 32,
|
| 68 |
+
"patch_size": 16,
|
| 69 |
+
"pooling_kernel_size": 3,
|
| 70 |
+
"resample": 3,
|
| 71 |
+
"rescale_factor": 0.00392156862745098,
|
| 72 |
+
"return_metadata": false,
|
| 73 |
+
"video_processor_type": "Gemma4VideoProcessor"
|
| 74 |
+
}
|
| 75 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
|
| 3 |
+
size 32169626
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": true,
|
| 21 |
+
"local_files_only": false,
|
| 22 |
+
"mask_token": "<mask>",
|
| 23 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 24 |
+
"model_specific_special_tokens": {
|
| 25 |
+
"audio_token": "<|audio|>",
|
| 26 |
+
"boa_token": "<|audio>",
|
| 27 |
+
"boi_token": "<|image>",
|
| 28 |
+
"eoa_token": "<audio|>",
|
| 29 |
+
"eoc_token": "<channel|>",
|
| 30 |
+
"eoi_token": "<image|>",
|
| 31 |
+
"eot_token": "<turn|>",
|
| 32 |
+
"escape_token": "<|\"|>",
|
| 33 |
+
"etc_token": "<tool_call|>",
|
| 34 |
+
"etd_token": "<tool|>",
|
| 35 |
+
"etr_token": "<tool_response|>",
|
| 36 |
+
"image_token": "<|image|>",
|
| 37 |
+
"soc_token": "<|channel>",
|
| 38 |
+
"sot_token": "<|turn>",
|
| 39 |
+
"stc_token": "<|tool_call>",
|
| 40 |
+
"std_token": "<|tool>",
|
| 41 |
+
"str_token": "<|tool_response>",
|
| 42 |
+
"think_token": "<|think|>"
|
| 43 |
+
},
|
| 44 |
+
"pad_token": "<pad>",
|
| 45 |
+
"padding_side": "left",
|
| 46 |
+
"processor_class": "Gemma4Processor",
|
| 47 |
+
"response_schema": {
|
| 48 |
+
"properties": {
|
| 49 |
+
"content": {
|
| 50 |
+
"type": "string"
|
| 51 |
+
},
|
| 52 |
+
"role": {
|
| 53 |
+
"const": "assistant"
|
| 54 |
+
},
|
| 55 |
+
"thinking": {
|
| 56 |
+
"type": "string"
|
| 57 |
+
},
|
| 58 |
+
"tool_calls": {
|
| 59 |
+
"items": {
|
| 60 |
+
"properties": {
|
| 61 |
+
"function": {
|
| 62 |
+
"properties": {
|
| 63 |
+
"arguments": {
|
| 64 |
+
"additionalProperties": {},
|
| 65 |
+
"type": "object",
|
| 66 |
+
"x-parser": "gemma4-tool-call"
|
| 67 |
+
},
|
| 68 |
+
"name": {
|
| 69 |
+
"type": "string"
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"type": "object",
|
| 73 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
|
| 74 |
+
},
|
| 75 |
+
"type": {
|
| 76 |
+
"const": "function"
|
| 77 |
+
}
|
| 78 |
+
},
|
| 79 |
+
"type": "object"
|
| 80 |
+
},
|
| 81 |
+
"type": "array",
|
| 82 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
|
| 83 |
+
}
|
| 84 |
+
},
|
| 85 |
+
"type": "object",
|
| 86 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
|
| 87 |
+
},
|
| 88 |
+
"soc_token": "<|channel>",
|
| 89 |
+
"sot_token": "<|turn>",
|
| 90 |
+
"stc_token": "<|tool_call>",
|
| 91 |
+
"std_token": "<|tool>",
|
| 92 |
+
"str_token": "<|tool_response>",
|
| 93 |
+
"think_token": "<|think|>",
|
| 94 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 95 |
+
"unk_token": "<unk>"
|
| 96 |
+
}
|