Add files using upload-large-folder tool
Browse files- README.md +4 -18
- chat_template.jinja +7 -0
- config.json +82 -39
- generation_config.json +2 -2
- model-00001-of-00005.safetensors +2 -2
- model-00002-of-00005.safetensors +2 -2
- model-00003-of-00005.safetensors +2 -2
- model-00004-of-00005.safetensors +2 -2
- model-00005-of-00005.safetensors +2 -2
- model.safetensors.index.json +448 -483
- tokenizer_config.json +4 -4
README.md
CHANGED
|
@@ -1,29 +1,15 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
pipeline_tag: image-text-to-text
|
| 7 |
tags:
|
| 8 |
- multimodal
|
|
|
|
| 9 |
library_name: transformers
|
| 10 |
---
|
| 11 |
-
<div>
|
| 12 |
-
<p style="margin-bottom: 0; margin-top: 0;">
|
| 13 |
-
<strong>See <a href="https://huggingface.co/collections/unsloth/qwen25-vl-all-versions-679ca6c784fad5bd976a05a1">our collection</a> for versions of Qwen2.5-VL including 4-bit & dynamic formats.</strong>
|
| 14 |
-
</p>
|
| 15 |
-
<div style="display: flex; gap: 5px; align-items: center; ">
|
| 16 |
-
<a href="https://github.com/unslothai/unsloth/">
|
| 17 |
-
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 18 |
-
</a>
|
| 19 |
-
<a href="https://discord.gg/unsloth">
|
| 20 |
-
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 21 |
-
</a>
|
| 22 |
-
<a href="https://docs.unsloth.ai/">
|
| 23 |
-
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 24 |
-
</a>
|
| 25 |
-
</div>
|
| 26 |
-
</div>
|
| 27 |
|
| 28 |
# Qwen2.5-VL-32B-Instruct
|
| 29 |
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
|
@@ -66,7 +52,7 @@ We extend dynamic resolution to the temporal dimension by adopting dynamic FPS s
|
|
| 66 |
We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM.
|
| 67 |
|
| 68 |
|
| 69 |
-
We have
|
| 70 |
|
| 71 |
|
| 72 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- Qwen/Qwen2.5-VL-32B-Instruct
|
| 4 |
license: apache-2.0
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
pipeline_tag: image-text-to-text
|
| 8 |
tags:
|
| 9 |
- multimodal
|
| 10 |
+
- unsloth
|
| 11 |
library_name: transformers
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# Qwen2.5-VL-32B-Instruct
|
| 15 |
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
|
|
|
| 52 |
We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM.
|
| 53 |
|
| 54 |
|
| 55 |
+
We have four models with 3, 7, 32 and 72 billion parameters. This repo contains the instruction-tuned 32B Qwen2.5-VL model. For more information, visit our [Blog](https://qwenlm.github.io/blog/qwen2.5-vl/) and [GitHub](https://github.com/QwenLM/Qwen2.5-VL).
|
| 56 |
|
| 57 |
|
| 58 |
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"image_token_id": 151655,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 27648,
|
| 12 |
-
"max_position_embeddings":
|
| 13 |
"max_window_layers": 64,
|
| 14 |
"model_type": "qwen2_5_vl",
|
| 15 |
"num_attention_heads": 40,
|
|
@@ -31,75 +31,78 @@
|
|
| 31 |
"merger",
|
| 32 |
"modality_projection",
|
| 33 |
"model.layers.10.mlp",
|
| 34 |
-
"model.layers.
|
| 35 |
-
"model.layers.22.mlp",
|
| 36 |
"model.layers.15.mlp",
|
| 37 |
-
"
|
|
|
|
|
|
|
| 38 |
"visual.blocks.27.attn",
|
|
|
|
| 39 |
"visual.blocks.28.attn",
|
|
|
|
| 40 |
"visual.blocks.31.attn",
|
|
|
|
|
|
|
| 41 |
"visual.merger.mlp",
|
| 42 |
"visual.blocks.30.mlp",
|
| 43 |
-
"visual.blocks.29.attn",
|
| 44 |
-
"visual.blocks.26.attn",
|
| 45 |
"visual.blocks.24.attn",
|
| 46 |
"visual.blocks.30.attn",
|
| 47 |
-
"visual.blocks.21.attn",
|
| 48 |
-
"visual.blocks.25.attn",
|
| 49 |
"visual.blocks.22.attn",
|
| 50 |
-
"visual.blocks.
|
| 51 |
-
"visual.blocks.19.attn",
|
| 52 |
"visual.blocks.20.attn",
|
|
|
|
| 53 |
"model.layers.6.mlp",
|
| 54 |
-
"visual.blocks.18.attn",
|
| 55 |
"visual.blocks.26.mlp",
|
|
|
|
| 56 |
"visual.blocks.27.mlp",
|
| 57 |
-
"visual.blocks.
|
| 58 |
-
"visual.blocks.18.mlp",
|
| 59 |
"visual.blocks.19.mlp",
|
| 60 |
-
"visual.blocks.
|
| 61 |
"visual.blocks.23.mlp",
|
| 62 |
-
"visual.blocks.
|
| 63 |
"visual.blocks.23.attn",
|
|
|
|
| 64 |
"visual.blocks.22.mlp",
|
| 65 |
-
"visual.blocks.
|
| 66 |
-
"visual.blocks.12.attn",
|
| 67 |
-
"visual.blocks.11.attn",
|
| 68 |
-
"visual.blocks.9.attn",
|
| 69 |
-
"visual.blocks.21.mlp",
|
| 70 |
-
"visual.blocks.16.attn",
|
| 71 |
"visual.blocks.14.attn",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"visual.blocks.10.mlp",
|
| 73 |
-
"visual.blocks.
|
|
|
|
|
|
|
| 74 |
"visual.blocks.13.attn",
|
| 75 |
-
"visual.blocks.
|
| 76 |
-
"visual.blocks.11.mlp",
|
| 77 |
-
"visual.blocks.9.mlp",
|
| 78 |
-
"visual.blocks.6.attn",
|
| 79 |
-
"visual.blocks.5.mlp",
|
| 80 |
-
"visual.blocks.12.mlp",
|
| 81 |
"visual.blocks.4.mlp",
|
| 82 |
-
"visual.blocks.
|
|
|
|
|
|
|
| 83 |
"visual.blocks.8.mlp",
|
| 84 |
-
"visual.blocks.
|
| 85 |
"visual.blocks.2.attn",
|
| 86 |
-
"visual.blocks.
|
| 87 |
-
"visual.blocks.
|
| 88 |
"visual.blocks.8.attn",
|
|
|
|
| 89 |
"visual.blocks.13.mlp",
|
| 90 |
-
"visual.blocks.
|
|
|
|
| 91 |
"visual.blocks.15.mlp",
|
| 92 |
-
"visual.blocks.2.mlp",
|
| 93 |
"visual.blocks.1.attn",
|
| 94 |
-
"visual.blocks.
|
| 95 |
-
"visual.blocks.0.attn",
|
| 96 |
"visual.blocks.15.attn",
|
| 97 |
-
"visual.blocks.4.attn",
|
| 98 |
"visual.blocks.7.attn",
|
|
|
|
|
|
|
|
|
|
| 99 |
"visual.blocks.3.attn",
|
|
|
|
| 100 |
"visual.blocks.14.mlp",
|
|
|
|
| 101 |
"visual.blocks.0.mlp",
|
| 102 |
-
"visual.blocks.
|
| 103 |
],
|
| 104 |
"llm_int8_threshold": 6.0,
|
| 105 |
"load_in_4bit": true,
|
|
@@ -118,9 +121,48 @@
|
|
| 118 |
},
|
| 119 |
"rope_theta": 1000000.0,
|
| 120 |
"sliding_window": 32768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
"tie_word_embeddings": false,
|
| 122 |
"torch_dtype": "bfloat16",
|
| 123 |
-
"transformers_version": "4.
|
| 124 |
"unsloth_fixed": true,
|
| 125 |
"use_cache": true,
|
| 126 |
"use_sliding_window": false,
|
|
@@ -137,6 +179,7 @@
|
|
| 137 |
"hidden_size": 1280,
|
| 138 |
"in_channels": 3,
|
| 139 |
"in_chans": 3,
|
|
|
|
| 140 |
"intermediate_size": 3456,
|
| 141 |
"model_type": "qwen2_5_vl",
|
| 142 |
"num_heads": 16,
|
|
|
|
| 9 |
"image_token_id": 151655,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 27648,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
"max_window_layers": 64,
|
| 14 |
"model_type": "qwen2_5_vl",
|
| 15 |
"num_attention_heads": 40,
|
|
|
|
| 31 |
"merger",
|
| 32 |
"modality_projection",
|
| 33 |
"model.layers.10.mlp",
|
| 34 |
+
"model.layers.16.mlp",
|
|
|
|
| 35 |
"model.layers.15.mlp",
|
| 36 |
+
"model.layers.5.mlp",
|
| 37 |
+
"model.layers.5.self_attn",
|
| 38 |
+
"model.layers.8.mlp",
|
| 39 |
"visual.blocks.27.attn",
|
| 40 |
+
"visual.blocks.31.mlp",
|
| 41 |
"visual.blocks.28.attn",
|
| 42 |
+
"visual.blocks.21.attn",
|
| 43 |
"visual.blocks.31.attn",
|
| 44 |
+
"visual.blocks.26.attn",
|
| 45 |
+
"visual.blocks.29.attn",
|
| 46 |
"visual.merger.mlp",
|
| 47 |
"visual.blocks.30.mlp",
|
|
|
|
|
|
|
| 48 |
"visual.blocks.24.attn",
|
| 49 |
"visual.blocks.30.attn",
|
|
|
|
|
|
|
| 50 |
"visual.blocks.22.attn",
|
| 51 |
+
"visual.blocks.25.attn",
|
|
|
|
| 52 |
"visual.blocks.20.attn",
|
| 53 |
+
"visual.blocks.29.mlp",
|
| 54 |
"model.layers.6.mlp",
|
|
|
|
| 55 |
"visual.blocks.26.mlp",
|
| 56 |
+
"visual.blocks.25.mlp",
|
| 57 |
"visual.blocks.27.mlp",
|
| 58 |
+
"visual.blocks.18.attn",
|
|
|
|
| 59 |
"visual.blocks.19.mlp",
|
| 60 |
+
"visual.blocks.19.attn",
|
| 61 |
"visual.blocks.23.mlp",
|
| 62 |
+
"visual.blocks.17.attn",
|
| 63 |
"visual.blocks.23.attn",
|
| 64 |
+
"visual.blocks.20.mlp",
|
| 65 |
"visual.blocks.22.mlp",
|
| 66 |
+
"visual.blocks.9.mlp",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"visual.blocks.14.attn",
|
| 68 |
+
"visual.blocks.18.mlp",
|
| 69 |
+
"visual.blocks.28.mlp",
|
| 70 |
+
"visual.blocks.24.mlp",
|
| 71 |
+
"visual.blocks.11.attn",
|
| 72 |
"visual.blocks.10.mlp",
|
| 73 |
+
"visual.blocks.6.mlp",
|
| 74 |
+
"visual.blocks.16.attn",
|
| 75 |
+
"visual.blocks.21.mlp",
|
| 76 |
"visual.blocks.13.attn",
|
| 77 |
+
"visual.blocks.12.attn",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
"visual.blocks.4.mlp",
|
| 79 |
+
"visual.blocks.10.attn",
|
| 80 |
+
"visual.blocks.11.mlp",
|
| 81 |
+
"visual.blocks.9.attn",
|
| 82 |
"visual.blocks.8.mlp",
|
| 83 |
+
"visual.blocks.16.mlp",
|
| 84 |
"visual.blocks.2.attn",
|
| 85 |
+
"visual.blocks.5.mlp",
|
| 86 |
+
"visual.blocks.2.mlp",
|
| 87 |
"visual.blocks.8.attn",
|
| 88 |
+
"visual.blocks.6.attn",
|
| 89 |
"visual.blocks.13.mlp",
|
| 90 |
+
"visual.blocks.7.mlp",
|
| 91 |
+
"visual.blocks.1.mlp",
|
| 92 |
"visual.blocks.15.mlp",
|
|
|
|
| 93 |
"visual.blocks.1.attn",
|
| 94 |
+
"visual.blocks.3.mlp",
|
|
|
|
| 95 |
"visual.blocks.15.attn",
|
|
|
|
| 96 |
"visual.blocks.7.attn",
|
| 97 |
+
"visual.blocks.12.mlp",
|
| 98 |
+
"visual.blocks.5.attn",
|
| 99 |
+
"visual.blocks.4.attn",
|
| 100 |
"visual.blocks.3.attn",
|
| 101 |
+
"visual.blocks.0.attn",
|
| 102 |
"visual.blocks.14.mlp",
|
| 103 |
+
"visual.blocks.17.mlp",
|
| 104 |
"visual.blocks.0.mlp",
|
| 105 |
+
"visual.blocks.31.mlp.down_proj"
|
| 106 |
],
|
| 107 |
"llm_int8_threshold": 6.0,
|
| 108 |
"load_in_4bit": true,
|
|
|
|
| 121 |
},
|
| 122 |
"rope_theta": 1000000.0,
|
| 123 |
"sliding_window": 32768,
|
| 124 |
+
"text_config": {
|
| 125 |
+
"architectures": [
|
| 126 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 127 |
+
],
|
| 128 |
+
"attention_dropout": 0.0,
|
| 129 |
+
"eos_token_id": 151645,
|
| 130 |
+
"hidden_act": "silu",
|
| 131 |
+
"hidden_size": 5120,
|
| 132 |
+
"image_token_id": null,
|
| 133 |
+
"initializer_range": 0.02,
|
| 134 |
+
"intermediate_size": 27648,
|
| 135 |
+
"max_position_embeddings": 128000,
|
| 136 |
+
"max_window_layers": 64,
|
| 137 |
+
"model_type": "qwen2_5_vl_text",
|
| 138 |
+
"num_attention_heads": 40,
|
| 139 |
+
"num_hidden_layers": 64,
|
| 140 |
+
"num_key_value_heads": 8,
|
| 141 |
+
"pad_token_id": 151643,
|
| 142 |
+
"rms_norm_eps": 1e-06,
|
| 143 |
+
"rope_scaling": {
|
| 144 |
+
"mrope_section": [
|
| 145 |
+
16,
|
| 146 |
+
24,
|
| 147 |
+
24
|
| 148 |
+
],
|
| 149 |
+
"rope_type": "default",
|
| 150 |
+
"type": "default"
|
| 151 |
+
},
|
| 152 |
+
"rope_theta": 1000000.0,
|
| 153 |
+
"sliding_window": 32768,
|
| 154 |
+
"torch_dtype": "bfloat16",
|
| 155 |
+
"use_cache": true,
|
| 156 |
+
"use_sliding_window": false,
|
| 157 |
+
"video_token_id": null,
|
| 158 |
+
"vision_end_token_id": 151653,
|
| 159 |
+
"vision_start_token_id": 151652,
|
| 160 |
+
"vision_token_id": 151654,
|
| 161 |
+
"vocab_size": 152064
|
| 162 |
+
},
|
| 163 |
"tie_word_embeddings": false,
|
| 164 |
"torch_dtype": "bfloat16",
|
| 165 |
+
"transformers_version": "4.52.0.dev0",
|
| 166 |
"unsloth_fixed": true,
|
| 167 |
"use_cache": true,
|
| 168 |
"use_sliding_window": false,
|
|
|
|
| 179 |
"hidden_size": 1280,
|
| 180 |
"in_channels": 3,
|
| 181 |
"in_chans": 3,
|
| 182 |
+
"initializer_range": 0.02,
|
| 183 |
"intermediate_size": 3456,
|
| 184 |
"model_type": "qwen2_5_vl",
|
| 185 |
"num_heads": 16,
|
generation_config.json
CHANGED
|
@@ -5,9 +5,9 @@
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
-
"max_length":
|
| 9 |
"pad_token_id": 151654,
|
| 10 |
"repetition_penalty": 1.05,
|
| 11 |
"temperature": 1e-06,
|
| 12 |
-
"transformers_version": "4.
|
| 13 |
}
|
|
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
+
"max_length": 128000,
|
| 9 |
"pad_token_id": 151654,
|
| 10 |
"repetition_penalty": 1.05,
|
| 11 |
"temperature": 1e-06,
|
| 12 |
+
"transformers_version": "4.52.0.dev0"
|
| 13 |
}
|
model-00001-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75e8b15c927cc3ae1737f61bc7b238d5e008a73b5e8052ee8f75189b710a70c1
|
| 3 |
+
size 4884840863
|
model-00002-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:614eb314745898b39031deafa6486b022a5272920cf7a2ffddd4e3d35293268d
|
| 3 |
+
size 4753752247
|
model-00003-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9822c75f53a00867e05736b063a57010714a63d2302c3bf66ba407bbdbd29cae
|
| 3 |
+
size 4989181706
|
model-00004-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36c7b46219878dff2dcf373aa56347da55958df1d9f9d5e0ae94c4b25e87eab0
|
| 3 |
+
size 4939613635
|
model-00005-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98cdc0eb48e4279e454248b2aa1937209041cf6a91007d8dbab5494742270310
|
| 3 |
+
size 4900743706
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00005-of-00005.safetensors",
|
|
@@ -319,11 +319,11 @@
|
|
| 319 |
"model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 320 |
"model.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 321 |
"model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 322 |
-
"model.layers.15.input_layernorm.weight": "model-
|
| 323 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
| 324 |
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 325 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
| 326 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
| 327 |
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 328 |
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 329 |
"model.layers.15.self_attn.k_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
|
@@ -351,53 +351,38 @@
|
|
| 351 |
"model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 352 |
"model.layers.15.self_attn.v_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 353 |
"model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 354 |
-
"model.layers.16.input_layernorm.weight": "model-
|
| 355 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
| 356 |
-
"model.layers.16.mlp.
|
| 357 |
-
"model.layers.16.mlp.
|
| 358 |
-
"model.layers.16.
|
| 359 |
-
"model.layers.16.
|
| 360 |
-
"model.layers.16.
|
| 361 |
-
"model.layers.16.
|
| 362 |
-
"model.layers.16.
|
| 363 |
-
"model.layers.16.
|
| 364 |
-
"model.layers.16.
|
| 365 |
-
"model.layers.16.
|
| 366 |
-
"model.layers.16.
|
| 367 |
-
"model.layers.16.
|
| 368 |
-
"model.layers.16.
|
| 369 |
-
"model.layers.16.
|
| 370 |
-
"model.layers.16.
|
| 371 |
-
"model.layers.16.
|
| 372 |
-
"model.layers.16.
|
| 373 |
-
"model.layers.16.
|
| 374 |
-
"model.layers.16.self_attn.
|
| 375 |
-
"model.layers.16.self_attn.
|
| 376 |
-
"model.layers.16.self_attn.
|
| 377 |
-
"model.layers.16.self_attn.
|
| 378 |
-
"model.layers.16.self_attn.
|
| 379 |
-
"model.layers.16.self_attn.
|
| 380 |
-
"model.layers.16.self_attn.
|
| 381 |
-
"model.layers.16.self_attn.
|
| 382 |
-
"model.layers.16.self_attn.
|
| 383 |
-
"model.layers.16.self_attn.
|
| 384 |
-
"model.layers.16.self_attn.
|
| 385 |
-
"model.layers.16.self_attn.
|
| 386 |
-
"model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 387 |
-
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 388 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 389 |
-
"model.layers.16.self_attn.q_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 390 |
-
"model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 391 |
-
"model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 392 |
-
"model.layers.16.self_attn.q_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 393 |
-
"model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 394 |
-
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 395 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 396 |
-
"model.layers.16.self_attn.v_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 397 |
-
"model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 398 |
-
"model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 399 |
-
"model.layers.16.self_attn.v_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 400 |
-
"model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 401 |
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 402 |
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 403 |
"model.layers.17.mlp.down_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
@@ -418,33 +403,33 @@
|
|
| 418 |
"model.layers.17.mlp.up_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 419 |
"model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 420 |
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 421 |
-
"model.layers.17.self_attn.k_proj.bias": "model-
|
| 422 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
| 423 |
-
"model.layers.17.self_attn.k_proj.weight.absmax": "model-
|
| 424 |
-
"model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-
|
| 425 |
-
"model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 426 |
-
"model.layers.17.self_attn.k_proj.weight.quant_map": "model-
|
| 427 |
-
"model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 428 |
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 429 |
"model.layers.17.self_attn.o_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 430 |
"model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 431 |
"model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 432 |
"model.layers.17.self_attn.o_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 433 |
"model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 434 |
-
"model.layers.17.self_attn.q_proj.bias": "model-
|
| 435 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
| 436 |
-
"model.layers.17.self_attn.q_proj.weight.absmax": "model-
|
| 437 |
-
"model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-
|
| 438 |
-
"model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 439 |
-
"model.layers.17.self_attn.q_proj.weight.quant_map": "model-
|
| 440 |
-
"model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 441 |
-
"model.layers.17.self_attn.v_proj.bias": "model-
|
| 442 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
| 443 |
-
"model.layers.17.self_attn.v_proj.weight.absmax": "model-
|
| 444 |
-
"model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-
|
| 445 |
-
"model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 446 |
-
"model.layers.17.self_attn.v_proj.weight.quant_map": "model-
|
| 447 |
-
"model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 448 |
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 449 |
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 450 |
"model.layers.18.mlp.down_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
@@ -682,8 +667,23 @@
|
|
| 682 |
"model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 683 |
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 684 |
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 685 |
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 686 |
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 687 |
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 688 |
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 689 |
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
|
@@ -1135,26 +1135,26 @@
|
|
| 1135 |
"model.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 1136 |
"model.layers.30.self_attn.v_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 1137 |
"model.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 1138 |
-
"model.layers.31.input_layernorm.weight": "model-
|
| 1139 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
| 1140 |
-
"model.layers.31.mlp.down_proj.weight.absmax": "model-
|
| 1141 |
-
"model.layers.31.mlp.down_proj.weight.nested_absmax": "model-
|
| 1142 |
-
"model.layers.31.mlp.down_proj.weight.nested_quant_map": "model-
|
| 1143 |
-
"model.layers.31.mlp.down_proj.weight.quant_map": "model-
|
| 1144 |
-
"model.layers.31.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1145 |
-
"model.layers.31.mlp.gate_proj.weight": "model-
|
| 1146 |
-
"model.layers.31.mlp.gate_proj.weight.absmax": "model-
|
| 1147 |
-
"model.layers.31.mlp.gate_proj.weight.nested_absmax": "model-
|
| 1148 |
-
"model.layers.31.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 1149 |
-
"model.layers.31.mlp.gate_proj.weight.quant_map": "model-
|
| 1150 |
-
"model.layers.31.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1151 |
-
"model.layers.31.mlp.up_proj.weight": "model-
|
| 1152 |
-
"model.layers.31.mlp.up_proj.weight.absmax": "model-
|
| 1153 |
-
"model.layers.31.mlp.up_proj.weight.nested_absmax": "model-
|
| 1154 |
-
"model.layers.31.mlp.up_proj.weight.nested_quant_map": "model-
|
| 1155 |
-
"model.layers.31.mlp.up_proj.weight.quant_map": "model-
|
| 1156 |
-
"model.layers.31.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1157 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
| 1158 |
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 1159 |
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 1160 |
"model.layers.31.self_attn.k_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
@@ -1162,12 +1162,12 @@
|
|
| 1162 |
"model.layers.31.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 1163 |
"model.layers.31.self_attn.k_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 1164 |
"model.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 1165 |
-
"model.layers.31.self_attn.o_proj.weight": "model-
|
| 1166 |
-
"model.layers.31.self_attn.o_proj.weight.absmax": "model-
|
| 1167 |
-
"model.layers.31.self_attn.o_proj.weight.nested_absmax": "model-
|
| 1168 |
-
"model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 1169 |
-
"model.layers.31.self_attn.o_proj.weight.quant_map": "model-
|
| 1170 |
-
"model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1171 |
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 1172 |
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 1173 |
"model.layers.31.self_attn.q_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
@@ -1182,100 +1182,100 @@
|
|
| 1182 |
"model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 1183 |
"model.layers.31.self_attn.v_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 1184 |
"model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 1185 |
-
"model.layers.32.input_layernorm.weight": "model-
|
| 1186 |
-
"model.layers.32.mlp.down_proj.weight": "model-
|
| 1187 |
-
"model.layers.32.mlp.down_proj.weight.absmax": "model-
|
| 1188 |
-
"model.layers.32.mlp.down_proj.weight.nested_absmax": "model-
|
| 1189 |
-
"model.layers.32.mlp.down_proj.weight.nested_quant_map": "model-
|
| 1190 |
-
"model.layers.32.mlp.down_proj.weight.quant_map": "model-
|
| 1191 |
-
"model.layers.32.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1192 |
-
"model.layers.32.mlp.gate_proj.weight": "model-
|
| 1193 |
-
"model.layers.32.mlp.gate_proj.weight.absmax": "model-
|
| 1194 |
-
"model.layers.32.mlp.gate_proj.weight.nested_absmax": "model-
|
| 1195 |
-
"model.layers.32.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 1196 |
-
"model.layers.32.mlp.gate_proj.weight.quant_map": "model-
|
| 1197 |
-
"model.layers.32.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1198 |
-
"model.layers.32.mlp.up_proj.weight": "model-
|
| 1199 |
-
"model.layers.32.mlp.up_proj.weight.absmax": "model-
|
| 1200 |
-
"model.layers.32.mlp.up_proj.weight.nested_absmax": "model-
|
| 1201 |
-
"model.layers.32.mlp.up_proj.weight.nested_quant_map": "model-
|
| 1202 |
-
"model.layers.32.mlp.up_proj.weight.quant_map": "model-
|
| 1203 |
-
"model.layers.32.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1204 |
-
"model.layers.32.post_attention_layernorm.weight": "model-
|
| 1205 |
-
"model.layers.32.self_attn.k_proj.bias": "model-
|
| 1206 |
-
"model.layers.32.self_attn.k_proj.weight": "model-
|
| 1207 |
-
"model.layers.32.self_attn.k_proj.weight.absmax": "model-
|
| 1208 |
-
"model.layers.32.self_attn.k_proj.weight.nested_absmax": "model-
|
| 1209 |
-
"model.layers.32.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 1210 |
-
"model.layers.32.self_attn.k_proj.weight.quant_map": "model-
|
| 1211 |
-
"model.layers.32.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1212 |
-
"model.layers.32.self_attn.o_proj.weight": "model-
|
| 1213 |
-
"model.layers.32.self_attn.o_proj.weight.absmax": "model-
|
| 1214 |
-
"model.layers.32.self_attn.o_proj.weight.nested_absmax": "model-
|
| 1215 |
-
"model.layers.32.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 1216 |
-
"model.layers.32.self_attn.o_proj.weight.quant_map": "model-
|
| 1217 |
-
"model.layers.32.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1218 |
-
"model.layers.32.self_attn.q_proj.bias": "model-
|
| 1219 |
-
"model.layers.32.self_attn.q_proj.weight": "model-
|
| 1220 |
-
"model.layers.32.self_attn.q_proj.weight.absmax": "model-
|
| 1221 |
-
"model.layers.32.self_attn.q_proj.weight.nested_absmax": "model-
|
| 1222 |
-
"model.layers.32.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 1223 |
-
"model.layers.32.self_attn.q_proj.weight.quant_map": "model-
|
| 1224 |
-
"model.layers.32.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1225 |
-
"model.layers.32.self_attn.v_proj.bias": "model-
|
| 1226 |
-
"model.layers.32.self_attn.v_proj.weight": "model-
|
| 1227 |
-
"model.layers.32.self_attn.v_proj.weight.absmax": "model-
|
| 1228 |
-
"model.layers.32.self_attn.v_proj.weight.nested_absmax": "model-
|
| 1229 |
-
"model.layers.32.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 1230 |
-
"model.layers.32.self_attn.v_proj.weight.quant_map": "model-
|
| 1231 |
-
"model.layers.32.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1232 |
-
"model.layers.33.input_layernorm.weight": "model-
|
| 1233 |
-
"model.layers.33.mlp.down_proj.weight": "model-
|
| 1234 |
-
"model.layers.33.mlp.down_proj.weight.absmax": "model-
|
| 1235 |
-
"model.layers.33.mlp.down_proj.weight.nested_absmax": "model-
|
| 1236 |
-
"model.layers.33.mlp.down_proj.weight.nested_quant_map": "model-
|
| 1237 |
-
"model.layers.33.mlp.down_proj.weight.quant_map": "model-
|
| 1238 |
-
"model.layers.33.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1239 |
-
"model.layers.33.mlp.gate_proj.weight": "model-
|
| 1240 |
-
"model.layers.33.mlp.gate_proj.weight.absmax": "model-
|
| 1241 |
-
"model.layers.33.mlp.gate_proj.weight.nested_absmax": "model-
|
| 1242 |
-
"model.layers.33.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 1243 |
-
"model.layers.33.mlp.gate_proj.weight.quant_map": "model-
|
| 1244 |
-
"model.layers.33.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1245 |
-
"model.layers.33.mlp.up_proj.weight": "model-
|
| 1246 |
-
"model.layers.33.mlp.up_proj.weight.absmax": "model-
|
| 1247 |
-
"model.layers.33.mlp.up_proj.weight.nested_absmax": "model-
|
| 1248 |
-
"model.layers.33.mlp.up_proj.weight.nested_quant_map": "model-
|
| 1249 |
-
"model.layers.33.mlp.up_proj.weight.quant_map": "model-
|
| 1250 |
-
"model.layers.33.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1251 |
-
"model.layers.33.post_attention_layernorm.weight": "model-
|
| 1252 |
-
"model.layers.33.self_attn.k_proj.bias": "model-
|
| 1253 |
-
"model.layers.33.self_attn.k_proj.weight": "model-
|
| 1254 |
-
"model.layers.33.self_attn.k_proj.weight.absmax": "model-
|
| 1255 |
-
"model.layers.33.self_attn.k_proj.weight.nested_absmax": "model-
|
| 1256 |
-
"model.layers.33.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 1257 |
-
"model.layers.33.self_attn.k_proj.weight.quant_map": "model-
|
| 1258 |
-
"model.layers.33.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1259 |
-
"model.layers.33.self_attn.o_proj.weight": "model-
|
| 1260 |
-
"model.layers.33.self_attn.o_proj.weight.absmax": "model-
|
| 1261 |
-
"model.layers.33.self_attn.o_proj.weight.nested_absmax": "model-
|
| 1262 |
-
"model.layers.33.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 1263 |
-
"model.layers.33.self_attn.o_proj.weight.quant_map": "model-
|
| 1264 |
-
"model.layers.33.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1265 |
-
"model.layers.33.self_attn.q_proj.bias": "model-
|
| 1266 |
-
"model.layers.33.self_attn.q_proj.weight": "model-
|
| 1267 |
-
"model.layers.33.self_attn.q_proj.weight.absmax": "model-
|
| 1268 |
-
"model.layers.33.self_attn.q_proj.weight.nested_absmax": "model-
|
| 1269 |
-
"model.layers.33.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 1270 |
-
"model.layers.33.self_attn.q_proj.weight.quant_map": "model-
|
| 1271 |
-
"model.layers.33.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1272 |
-
"model.layers.33.self_attn.v_proj.bias": "model-
|
| 1273 |
-
"model.layers.33.self_attn.v_proj.weight": "model-
|
| 1274 |
-
"model.layers.33.self_attn.v_proj.weight.absmax": "model-
|
| 1275 |
-
"model.layers.33.self_attn.v_proj.weight.nested_absmax": "model-
|
| 1276 |
-
"model.layers.33.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 1277 |
-
"model.layers.33.self_attn.v_proj.weight.quant_map": "model-
|
| 1278 |
-
"model.layers.33.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1279 |
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1280 |
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1281 |
"model.layers.34.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
|
@@ -1283,12 +1283,12 @@
|
|
| 1283 |
"model.layers.34.mlp.down_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1284 |
"model.layers.34.mlp.down_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1285 |
"model.layers.34.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1286 |
-
"model.layers.34.mlp.gate_proj.weight": "model-
|
| 1287 |
-
"model.layers.34.mlp.gate_proj.weight.absmax": "model-
|
| 1288 |
-
"model.layers.34.mlp.gate_proj.weight.nested_absmax": "model-
|
| 1289 |
-
"model.layers.34.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 1290 |
-
"model.layers.34.mlp.gate_proj.weight.quant_map": "model-
|
| 1291 |
-
"model.layers.34.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1292 |
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 1293 |
"model.layers.34.mlp.up_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1294 |
"model.layers.34.mlp.up_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
|
@@ -1296,33 +1296,33 @@
|
|
| 1296 |
"model.layers.34.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1297 |
"model.layers.34.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1298 |
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1299 |
-
"model.layers.34.self_attn.k_proj.bias": "model-
|
| 1300 |
-
"model.layers.34.self_attn.k_proj.weight": "model-
|
| 1301 |
-
"model.layers.34.self_attn.k_proj.weight.absmax": "model-
|
| 1302 |
-
"model.layers.34.self_attn.k_proj.weight.nested_absmax": "model-
|
| 1303 |
-
"model.layers.34.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 1304 |
-
"model.layers.34.self_attn.k_proj.weight.quant_map": "model-
|
| 1305 |
-
"model.layers.34.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1306 |
-
"model.layers.34.self_attn.o_proj.weight": "model-
|
| 1307 |
-
"model.layers.34.self_attn.o_proj.weight.absmax": "model-
|
| 1308 |
-
"model.layers.34.self_attn.o_proj.weight.nested_absmax": "model-
|
| 1309 |
-
"model.layers.34.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 1310 |
-
"model.layers.34.self_attn.o_proj.weight.quant_map": "model-
|
| 1311 |
-
"model.layers.34.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1312 |
-
"model.layers.34.self_attn.q_proj.bias": "model-
|
| 1313 |
-
"model.layers.34.self_attn.q_proj.weight": "model-
|
| 1314 |
-
"model.layers.34.self_attn.q_proj.weight.absmax": "model-
|
| 1315 |
-
"model.layers.34.self_attn.q_proj.weight.nested_absmax": "model-
|
| 1316 |
-
"model.layers.34.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 1317 |
-
"model.layers.34.self_attn.q_proj.weight.quant_map": "model-
|
| 1318 |
-
"model.layers.34.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1319 |
-
"model.layers.34.self_attn.v_proj.bias": "model-
|
| 1320 |
-
"model.layers.34.self_attn.v_proj.weight": "model-
|
| 1321 |
-
"model.layers.34.self_attn.v_proj.weight.absmax": "model-
|
| 1322 |
-
"model.layers.34.self_attn.v_proj.weight.nested_absmax": "model-
|
| 1323 |
-
"model.layers.34.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 1324 |
-
"model.layers.34.self_attn.v_proj.weight.quant_map": "model-
|
| 1325 |
-
"model.layers.34.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 1326 |
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1327 |
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1328 |
"model.layers.35.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
|
@@ -2075,60 +2075,25 @@
|
|
| 2075 |
"model.layers.49.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2076 |
"model.layers.49.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2077 |
"model.layers.49.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2078 |
-
"model.layers.5.input_layernorm.weight": "model-
|
| 2079 |
-
"model.layers.5.mlp.down_proj.weight": "model-
|
| 2080 |
-
"model.layers.5.mlp.down_proj.weight.absmax": "model-00001-of-00005.safetensors",
|
| 2081 |
-
"model.layers.5.mlp.down_proj.weight.nested_absmax": "model-00001-of-00005.safetensors",
|
| 2082 |
-
"model.layers.5.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00005.safetensors",
|
| 2083 |
-
"model.layers.5.mlp.down_proj.weight.quant_map": "model-00001-of-00005.safetensors",
|
| 2084 |
-
"model.layers.5.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00005.safetensors",
|
| 2085 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 2086 |
-
"model.layers.5.mlp.gate_proj.weight.absmax": "model-00001-of-00005.safetensors",
|
| 2087 |
-
"model.layers.5.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00005.safetensors",
|
| 2088 |
-
"model.layers.5.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00005.safetensors",
|
| 2089 |
-
"model.layers.5.mlp.gate_proj.weight.quant_map": "model-00001-of-00005.safetensors",
|
| 2090 |
-
"model.layers.5.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00005.safetensors",
|
| 2091 |
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 2092 |
-
"model.layers.5.
|
| 2093 |
-
"model.layers.5.mlp.up_proj.weight.nested_absmax": "model-00001-of-00005.safetensors",
|
| 2094 |
-
"model.layers.5.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00005.safetensors",
|
| 2095 |
-
"model.layers.5.mlp.up_proj.weight.quant_map": "model-00001-of-00005.safetensors",
|
| 2096 |
-
"model.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00005.safetensors",
|
| 2097 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 2098 |
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
| 2099 |
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 2100 |
-
"model.layers.5.self_attn.k_proj.weight.absmax": "model-00001-of-00005.safetensors",
|
| 2101 |
-
"model.layers.5.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00005.safetensors",
|
| 2102 |
-
"model.layers.5.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00005.safetensors",
|
| 2103 |
-
"model.layers.5.self_attn.k_proj.weight.quant_map": "model-00001-of-00005.safetensors",
|
| 2104 |
-
"model.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00005.safetensors",
|
| 2105 |
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 2106 |
-
"model.layers.5.self_attn.o_proj.weight.absmax": "model-00001-of-00005.safetensors",
|
| 2107 |
-
"model.layers.5.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00005.safetensors",
|
| 2108 |
-
"model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00005.safetensors",
|
| 2109 |
-
"model.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00005.safetensors",
|
| 2110 |
-
"model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00005.safetensors",
|
| 2111 |
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 2112 |
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 2113 |
-
"model.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00005.safetensors",
|
| 2114 |
-
"model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00005.safetensors",
|
| 2115 |
-
"model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00005.safetensors",
|
| 2116 |
-
"model.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00005.safetensors",
|
| 2117 |
-
"model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00005.safetensors",
|
| 2118 |
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 2119 |
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 2120 |
-
"model.layers.
|
| 2121 |
-
"model.layers.
|
| 2122 |
-
"model.layers.
|
| 2123 |
-
"model.layers.
|
| 2124 |
-
"model.layers.
|
| 2125 |
-
"model.layers.50.
|
| 2126 |
-
"model.layers.50.mlp.down_proj.weight": "model-
|
| 2127 |
-
"model.layers.50.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 2128 |
-
"model.layers.50.mlp.down_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 2129 |
-
"model.layers.50.mlp.down_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2130 |
-
"model.layers.50.mlp.down_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2131 |
-
"model.layers.50.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2132 |
"model.layers.50.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 2133 |
"model.layers.50.mlp.gate_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 2134 |
"model.layers.50.mlp.gate_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
|
@@ -2141,7 +2106,7 @@
|
|
| 2141 |
"model.layers.50.mlp.up_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2142 |
"model.layers.50.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2143 |
"model.layers.50.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2144 |
-
"model.layers.50.post_attention_layernorm.weight": "model-
|
| 2145 |
"model.layers.50.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 2146 |
"model.layers.50.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 2147 |
"model.layers.50.self_attn.k_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
|
@@ -2169,147 +2134,147 @@
|
|
| 2169 |
"model.layers.50.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2170 |
"model.layers.50.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2171 |
"model.layers.50.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2172 |
-
"model.layers.51.input_layernorm.weight": "model-
|
| 2173 |
-
"model.layers.51.mlp.down_proj.weight": "model-
|
| 2174 |
-
"model.layers.51.mlp.down_proj.weight.absmax": "model-
|
| 2175 |
-
"model.layers.51.mlp.down_proj.weight.nested_absmax": "model-
|
| 2176 |
-
"model.layers.51.mlp.down_proj.weight.nested_quant_map": "model-
|
| 2177 |
-
"model.layers.51.mlp.down_proj.weight.quant_map": "model-
|
| 2178 |
-
"model.layers.51.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2179 |
-
"model.layers.51.mlp.gate_proj.weight": "model-
|
| 2180 |
-
"model.layers.51.mlp.gate_proj.weight.absmax": "model-
|
| 2181 |
-
"model.layers.51.mlp.gate_proj.weight.nested_absmax": "model-
|
| 2182 |
-
"model.layers.51.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 2183 |
-
"model.layers.51.mlp.gate_proj.weight.quant_map": "model-
|
| 2184 |
-
"model.layers.51.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2185 |
-
"model.layers.51.mlp.up_proj.weight": "model-
|
| 2186 |
-
"model.layers.51.mlp.up_proj.weight.absmax": "model-
|
| 2187 |
-
"model.layers.51.mlp.up_proj.weight.nested_absmax": "model-
|
| 2188 |
-
"model.layers.51.mlp.up_proj.weight.nested_quant_map": "model-
|
| 2189 |
-
"model.layers.51.mlp.up_proj.weight.quant_map": "model-
|
| 2190 |
-
"model.layers.51.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2191 |
-
"model.layers.51.post_attention_layernorm.weight": "model-
|
| 2192 |
-
"model.layers.51.self_attn.k_proj.bias": "model-
|
| 2193 |
-
"model.layers.51.self_attn.k_proj.weight": "model-
|
| 2194 |
-
"model.layers.51.self_attn.k_proj.weight.absmax": "model-
|
| 2195 |
-
"model.layers.51.self_attn.k_proj.weight.nested_absmax": "model-
|
| 2196 |
-
"model.layers.51.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 2197 |
-
"model.layers.51.self_attn.k_proj.weight.quant_map": "model-
|
| 2198 |
-
"model.layers.51.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2199 |
-
"model.layers.51.self_attn.o_proj.weight": "model-
|
| 2200 |
-
"model.layers.51.self_attn.o_proj.weight.absmax": "model-
|
| 2201 |
-
"model.layers.51.self_attn.o_proj.weight.nested_absmax": "model-
|
| 2202 |
-
"model.layers.51.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 2203 |
-
"model.layers.51.self_attn.o_proj.weight.quant_map": "model-
|
| 2204 |
-
"model.layers.51.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2205 |
-
"model.layers.51.self_attn.q_proj.bias": "model-
|
| 2206 |
-
"model.layers.51.self_attn.q_proj.weight": "model-
|
| 2207 |
-
"model.layers.51.self_attn.q_proj.weight.absmax": "model-
|
| 2208 |
-
"model.layers.51.self_attn.q_proj.weight.nested_absmax": "model-
|
| 2209 |
-
"model.layers.51.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 2210 |
-
"model.layers.51.self_attn.q_proj.weight.quant_map": "model-
|
| 2211 |
-
"model.layers.51.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2212 |
-
"model.layers.51.self_attn.v_proj.bias": "model-
|
| 2213 |
-
"model.layers.51.self_attn.v_proj.weight": "model-
|
| 2214 |
-
"model.layers.51.self_attn.v_proj.weight.absmax": "model-
|
| 2215 |
-
"model.layers.51.self_attn.v_proj.weight.nested_absmax": "model-
|
| 2216 |
-
"model.layers.51.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 2217 |
-
"model.layers.51.self_attn.v_proj.weight.quant_map": "model-
|
| 2218 |
-
"model.layers.51.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2219 |
-
"model.layers.52.input_layernorm.weight": "model-
|
| 2220 |
-
"model.layers.52.mlp.down_proj.weight": "model-
|
| 2221 |
-
"model.layers.52.mlp.down_proj.weight.absmax": "model-
|
| 2222 |
-
"model.layers.52.mlp.down_proj.weight.nested_absmax": "model-
|
| 2223 |
-
"model.layers.52.mlp.down_proj.weight.nested_quant_map": "model-
|
| 2224 |
-
"model.layers.52.mlp.down_proj.weight.quant_map": "model-
|
| 2225 |
-
"model.layers.52.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2226 |
-
"model.layers.52.mlp.gate_proj.weight": "model-
|
| 2227 |
-
"model.layers.52.mlp.gate_proj.weight.absmax": "model-
|
| 2228 |
-
"model.layers.52.mlp.gate_proj.weight.nested_absmax": "model-
|
| 2229 |
-
"model.layers.52.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 2230 |
-
"model.layers.52.mlp.gate_proj.weight.quant_map": "model-
|
| 2231 |
-
"model.layers.52.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2232 |
-
"model.layers.52.mlp.up_proj.weight": "model-
|
| 2233 |
-
"model.layers.52.mlp.up_proj.weight.absmax": "model-
|
| 2234 |
-
"model.layers.52.mlp.up_proj.weight.nested_absmax": "model-
|
| 2235 |
-
"model.layers.52.mlp.up_proj.weight.nested_quant_map": "model-
|
| 2236 |
-
"model.layers.52.mlp.up_proj.weight.quant_map": "model-
|
| 2237 |
-
"model.layers.52.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2238 |
-
"model.layers.52.post_attention_layernorm.weight": "model-
|
| 2239 |
-
"model.layers.52.self_attn.k_proj.bias": "model-
|
| 2240 |
-
"model.layers.52.self_attn.k_proj.weight": "model-
|
| 2241 |
-
"model.layers.52.self_attn.k_proj.weight.absmax": "model-
|
| 2242 |
-
"model.layers.52.self_attn.k_proj.weight.nested_absmax": "model-
|
| 2243 |
-
"model.layers.52.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 2244 |
-
"model.layers.52.self_attn.k_proj.weight.quant_map": "model-
|
| 2245 |
-
"model.layers.52.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2246 |
-
"model.layers.52.self_attn.o_proj.weight": "model-
|
| 2247 |
-
"model.layers.52.self_attn.o_proj.weight.absmax": "model-
|
| 2248 |
-
"model.layers.52.self_attn.o_proj.weight.nested_absmax": "model-
|
| 2249 |
-
"model.layers.52.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 2250 |
-
"model.layers.52.self_attn.o_proj.weight.quant_map": "model-
|
| 2251 |
-
"model.layers.52.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2252 |
-
"model.layers.52.self_attn.q_proj.bias": "model-
|
| 2253 |
-
"model.layers.52.self_attn.q_proj.weight": "model-
|
| 2254 |
-
"model.layers.52.self_attn.q_proj.weight.absmax": "model-
|
| 2255 |
-
"model.layers.52.self_attn.q_proj.weight.nested_absmax": "model-
|
| 2256 |
-
"model.layers.52.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 2257 |
-
"model.layers.52.self_attn.q_proj.weight.quant_map": "model-
|
| 2258 |
-
"model.layers.52.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2259 |
-
"model.layers.52.self_attn.v_proj.bias": "model-
|
| 2260 |
-
"model.layers.52.self_attn.v_proj.weight": "model-
|
| 2261 |
-
"model.layers.52.self_attn.v_proj.weight.absmax": "model-
|
| 2262 |
-
"model.layers.52.self_attn.v_proj.weight.nested_absmax": "model-
|
| 2263 |
-
"model.layers.52.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 2264 |
-
"model.layers.52.self_attn.v_proj.weight.quant_map": "model-
|
| 2265 |
-
"model.layers.52.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2266 |
-
"model.layers.53.input_layernorm.weight": "model-
|
| 2267 |
-
"model.layers.53.mlp.down_proj.weight": "model-
|
| 2268 |
-
"model.layers.53.mlp.down_proj.weight.absmax": "model-
|
| 2269 |
-
"model.layers.53.mlp.down_proj.weight.nested_absmax": "model-
|
| 2270 |
-
"model.layers.53.mlp.down_proj.weight.nested_quant_map": "model-
|
| 2271 |
-
"model.layers.53.mlp.down_proj.weight.quant_map": "model-
|
| 2272 |
-
"model.layers.53.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2273 |
-
"model.layers.53.mlp.gate_proj.weight": "model-
|
| 2274 |
-
"model.layers.53.mlp.gate_proj.weight.absmax": "model-
|
| 2275 |
-
"model.layers.53.mlp.gate_proj.weight.nested_absmax": "model-
|
| 2276 |
-
"model.layers.53.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 2277 |
-
"model.layers.53.mlp.gate_proj.weight.quant_map": "model-
|
| 2278 |
-
"model.layers.53.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2279 |
-
"model.layers.53.mlp.up_proj.weight": "model-
|
| 2280 |
-
"model.layers.53.mlp.up_proj.weight.absmax": "model-
|
| 2281 |
-
"model.layers.53.mlp.up_proj.weight.nested_absmax": "model-
|
| 2282 |
-
"model.layers.53.mlp.up_proj.weight.nested_quant_map": "model-
|
| 2283 |
-
"model.layers.53.mlp.up_proj.weight.quant_map": "model-
|
| 2284 |
-
"model.layers.53.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2285 |
-
"model.layers.53.post_attention_layernorm.weight": "model-
|
| 2286 |
-
"model.layers.53.self_attn.k_proj.bias": "model-
|
| 2287 |
-
"model.layers.53.self_attn.k_proj.weight": "model-
|
| 2288 |
-
"model.layers.53.self_attn.k_proj.weight.absmax": "model-
|
| 2289 |
-
"model.layers.53.self_attn.k_proj.weight.nested_absmax": "model-
|
| 2290 |
-
"model.layers.53.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 2291 |
-
"model.layers.53.self_attn.k_proj.weight.quant_map": "model-
|
| 2292 |
-
"model.layers.53.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2293 |
-
"model.layers.53.self_attn.o_proj.weight": "model-
|
| 2294 |
-
"model.layers.53.self_attn.o_proj.weight.absmax": "model-
|
| 2295 |
-
"model.layers.53.self_attn.o_proj.weight.nested_absmax": "model-
|
| 2296 |
-
"model.layers.53.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 2297 |
-
"model.layers.53.self_attn.o_proj.weight.quant_map": "model-
|
| 2298 |
-
"model.layers.53.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2299 |
-
"model.layers.53.self_attn.q_proj.bias": "model-
|
| 2300 |
-
"model.layers.53.self_attn.q_proj.weight": "model-
|
| 2301 |
-
"model.layers.53.self_attn.q_proj.weight.absmax": "model-
|
| 2302 |
-
"model.layers.53.self_attn.q_proj.weight.nested_absmax": "model-
|
| 2303 |
-
"model.layers.53.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 2304 |
-
"model.layers.53.self_attn.q_proj.weight.quant_map": "model-
|
| 2305 |
-
"model.layers.53.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2306 |
-
"model.layers.53.self_attn.v_proj.bias": "model-
|
| 2307 |
-
"model.layers.53.self_attn.v_proj.weight": "model-
|
| 2308 |
-
"model.layers.53.self_attn.v_proj.weight.absmax": "model-
|
| 2309 |
-
"model.layers.53.self_attn.v_proj.weight.nested_absmax": "model-
|
| 2310 |
-
"model.layers.53.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 2311 |
-
"model.layers.53.self_attn.v_proj.weight.quant_map": "model-
|
| 2312 |
-
"model.layers.53.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2313 |
"model.layers.54.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2314 |
"model.layers.54.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2315 |
"model.layers.54.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
|
@@ -2330,33 +2295,33 @@
|
|
| 2330 |
"model.layers.54.mlp.up_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2331 |
"model.layers.54.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2332 |
"model.layers.54.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2333 |
-
"model.layers.54.self_attn.k_proj.bias": "model-
|
| 2334 |
-
"model.layers.54.self_attn.k_proj.weight": "model-
|
| 2335 |
-
"model.layers.54.self_attn.k_proj.weight.absmax": "model-
|
| 2336 |
-
"model.layers.54.self_attn.k_proj.weight.nested_absmax": "model-
|
| 2337 |
-
"model.layers.54.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 2338 |
-
"model.layers.54.self_attn.k_proj.weight.quant_map": "model-
|
| 2339 |
-
"model.layers.54.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2340 |
-
"model.layers.54.self_attn.o_proj.weight": "model-
|
| 2341 |
-
"model.layers.54.self_attn.o_proj.weight.absmax": "model-
|
| 2342 |
-
"model.layers.54.self_attn.o_proj.weight.nested_absmax": "model-
|
| 2343 |
-
"model.layers.54.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 2344 |
-
"model.layers.54.self_attn.o_proj.weight.quant_map": "model-
|
| 2345 |
-
"model.layers.54.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2346 |
-
"model.layers.54.self_attn.q_proj.bias": "model-
|
| 2347 |
-
"model.layers.54.self_attn.q_proj.weight": "model-
|
| 2348 |
-
"model.layers.54.self_attn.q_proj.weight.absmax": "model-
|
| 2349 |
-
"model.layers.54.self_attn.q_proj.weight.nested_absmax": "model-
|
| 2350 |
-
"model.layers.54.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 2351 |
-
"model.layers.54.self_attn.q_proj.weight.quant_map": "model-
|
| 2352 |
-
"model.layers.54.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2353 |
-
"model.layers.54.self_attn.v_proj.bias": "model-
|
| 2354 |
-
"model.layers.54.self_attn.v_proj.weight": "model-
|
| 2355 |
-
"model.layers.54.self_attn.v_proj.weight.absmax": "model-
|
| 2356 |
-
"model.layers.54.self_attn.v_proj.weight.nested_absmax": "model-
|
| 2357 |
-
"model.layers.54.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 2358 |
-
"model.layers.54.self_attn.v_proj.weight.quant_map": "model-
|
| 2359 |
-
"model.layers.54.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2360 |
"model.layers.55.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2361 |
"model.layers.55.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2362 |
"model.layers.55.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
|
@@ -2594,36 +2559,36 @@
|
|
| 2594 |
"model.layers.59.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2595 |
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2596 |
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 2597 |
-
"model.layers.6.mlp.gate_proj.weight": "model-
|
| 2598 |
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 2599 |
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2600 |
-
"model.layers.6.self_attn.k_proj.bias": "model-
|
| 2601 |
-
"model.layers.6.self_attn.k_proj.weight": "model-
|
| 2602 |
-
"model.layers.6.self_attn.k_proj.weight.absmax": "model-
|
| 2603 |
-
"model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-
|
| 2604 |
-
"model.layers.6.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 2605 |
-
"model.layers.6.self_attn.k_proj.weight.quant_map": "model-
|
| 2606 |
-
"model.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2607 |
-
"model.layers.6.self_attn.o_proj.weight": "model-
|
| 2608 |
-
"model.layers.6.self_attn.o_proj.weight.absmax": "model-
|
| 2609 |
-
"model.layers.6.self_attn.o_proj.weight.nested_absmax": "model-
|
| 2610 |
-
"model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 2611 |
-
"model.layers.6.self_attn.o_proj.weight.quant_map": "model-
|
| 2612 |
-
"model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2613 |
-
"model.layers.6.self_attn.q_proj.bias": "model-
|
| 2614 |
-
"model.layers.6.self_attn.q_proj.weight": "model-
|
| 2615 |
-
"model.layers.6.self_attn.q_proj.weight.absmax": "model-
|
| 2616 |
-
"model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-
|
| 2617 |
-
"model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 2618 |
-
"model.layers.6.self_attn.q_proj.weight.quant_map": "model-
|
| 2619 |
-
"model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2620 |
-
"model.layers.6.self_attn.v_proj.bias": "model-
|
| 2621 |
-
"model.layers.6.self_attn.v_proj.weight": "model-
|
| 2622 |
-
"model.layers.6.self_attn.v_proj.weight.absmax": "model-
|
| 2623 |
-
"model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-
|
| 2624 |
-
"model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 2625 |
-
"model.layers.6.self_attn.v_proj.weight.quant_map": "model-
|
| 2626 |
-
"model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 2627 |
"model.layers.60.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2628 |
"model.layers.60.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2629 |
"model.layers.60.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
|
@@ -2814,8 +2779,23 @@
|
|
| 2814 |
"model.layers.63.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2815 |
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2816 |
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2817 |
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2818 |
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2819 |
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2820 |
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 2821 |
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
|
@@ -2846,23 +2826,8 @@
|
|
| 2846 |
"model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2847 |
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2848 |
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 2849 |
-
"model.layers.8.mlp.down_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2850 |
-
"model.layers.8.mlp.down_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2851 |
-
"model.layers.8.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2852 |
-
"model.layers.8.mlp.down_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2853 |
-
"model.layers.8.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2854 |
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 2855 |
-
"model.layers.8.mlp.gate_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2856 |
-
"model.layers.8.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2857 |
-
"model.layers.8.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2858 |
-
"model.layers.8.mlp.gate_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2859 |
-
"model.layers.8.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2860 |
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 2861 |
-
"model.layers.8.mlp.up_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2862 |
-
"model.layers.8.mlp.up_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2863 |
-
"model.layers.8.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2864 |
-
"model.layers.8.mlp.up_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2865 |
-
"model.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2866 |
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2867 |
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 2868 |
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 24467745165
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00005-of-00005.safetensors",
|
|
|
|
| 319 |
"model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 320 |
"model.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 321 |
"model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 322 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 323 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 324 |
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 325 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 326 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 327 |
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 328 |
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 329 |
"model.layers.15.self_attn.k_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
|
|
|
| 351 |
"model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 352 |
"model.layers.15.self_attn.v_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 353 |
"model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 354 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 355 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 356 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 357 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 358 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 359 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 360 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 361 |
+
"model.layers.16.self_attn.k_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 362 |
+
"model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 363 |
+
"model.layers.16.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 364 |
+
"model.layers.16.self_attn.k_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 365 |
+
"model.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 366 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 367 |
+
"model.layers.16.self_attn.o_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 368 |
+
"model.layers.16.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 369 |
+
"model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 370 |
+
"model.layers.16.self_attn.o_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 371 |
+
"model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 372 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 373 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 374 |
+
"model.layers.16.self_attn.q_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 375 |
+
"model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 376 |
+
"model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 377 |
+
"model.layers.16.self_attn.q_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 378 |
+
"model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 379 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 380 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 381 |
+
"model.layers.16.self_attn.v_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 382 |
+
"model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 383 |
+
"model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 384 |
+
"model.layers.16.self_attn.v_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 385 |
+
"model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 386 |
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 387 |
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 388 |
"model.layers.17.mlp.down_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
|
|
| 403 |
"model.layers.17.mlp.up_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 404 |
"model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 405 |
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 406 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 407 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 408 |
+
"model.layers.17.self_attn.k_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 409 |
+
"model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 410 |
+
"model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 411 |
+
"model.layers.17.self_attn.k_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 412 |
+
"model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 413 |
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 414 |
"model.layers.17.self_attn.o_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 415 |
"model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 416 |
"model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 417 |
"model.layers.17.self_attn.o_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 418 |
"model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 419 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 420 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 421 |
+
"model.layers.17.self_attn.q_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 422 |
+
"model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 423 |
+
"model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 424 |
+
"model.layers.17.self_attn.q_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 425 |
+
"model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 426 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 427 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 428 |
+
"model.layers.17.self_attn.v_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 429 |
+
"model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 430 |
+
"model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 431 |
+
"model.layers.17.self_attn.v_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 432 |
+
"model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 433 |
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 434 |
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 435 |
"model.layers.18.mlp.down_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
|
|
| 667 |
"model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 668 |
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 669 |
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 670 |
+
"model.layers.22.mlp.down_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 671 |
+
"model.layers.22.mlp.down_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 672 |
+
"model.layers.22.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 673 |
+
"model.layers.22.mlp.down_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 674 |
+
"model.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 675 |
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 676 |
+
"model.layers.22.mlp.gate_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 677 |
+
"model.layers.22.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 678 |
+
"model.layers.22.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 679 |
+
"model.layers.22.mlp.gate_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 680 |
+
"model.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 681 |
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 682 |
+
"model.layers.22.mlp.up_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
| 683 |
+
"model.layers.22.mlp.up_proj.weight.nested_absmax": "model-00003-of-00005.safetensors",
|
| 684 |
+
"model.layers.22.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 685 |
+
"model.layers.22.mlp.up_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 686 |
+
"model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 687 |
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 688 |
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 689 |
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
|
|
|
| 1135 |
"model.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 1136 |
"model.layers.30.self_attn.v_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 1137 |
"model.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 1138 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1139 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1140 |
+
"model.layers.31.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1141 |
+
"model.layers.31.mlp.down_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1142 |
+
"model.layers.31.mlp.down_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1143 |
+
"model.layers.31.mlp.down_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1144 |
+
"model.layers.31.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1145 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 1146 |
+
"model.layers.31.mlp.gate_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1147 |
+
"model.layers.31.mlp.gate_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1148 |
+
"model.layers.31.mlp.gate_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1149 |
+
"model.layers.31.mlp.gate_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1150 |
+
"model.layers.31.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1151 |
+
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 1152 |
+
"model.layers.31.mlp.up_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1153 |
+
"model.layers.31.mlp.up_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1154 |
+
"model.layers.31.mlp.up_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1155 |
+
"model.layers.31.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1156 |
+
"model.layers.31.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1157 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1158 |
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 1159 |
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 1160 |
"model.layers.31.self_attn.k_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
|
|
| 1162 |
"model.layers.31.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 1163 |
"model.layers.31.self_attn.k_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 1164 |
"model.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 1165 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 1166 |
+
"model.layers.31.self_attn.o_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1167 |
+
"model.layers.31.self_attn.o_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1168 |
+
"model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1169 |
+
"model.layers.31.self_attn.o_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1170 |
+
"model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1171 |
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 1172 |
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 1173 |
"model.layers.31.self_attn.q_proj.weight.absmax": "model-00003-of-00005.safetensors",
|
|
|
|
| 1182 |
"model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00005.safetensors",
|
| 1183 |
"model.layers.31.self_attn.v_proj.weight.quant_map": "model-00003-of-00005.safetensors",
|
| 1184 |
"model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00005.safetensors",
|
| 1185 |
+
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1186 |
+
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1187 |
+
"model.layers.32.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1188 |
+
"model.layers.32.mlp.down_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1189 |
+
"model.layers.32.mlp.down_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1190 |
+
"model.layers.32.mlp.down_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1191 |
+
"model.layers.32.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1192 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 1193 |
+
"model.layers.32.mlp.gate_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1194 |
+
"model.layers.32.mlp.gate_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1195 |
+
"model.layers.32.mlp.gate_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1196 |
+
"model.layers.32.mlp.gate_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1197 |
+
"model.layers.32.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1198 |
+
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 1199 |
+
"model.layers.32.mlp.up_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1200 |
+
"model.layers.32.mlp.up_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1201 |
+
"model.layers.32.mlp.up_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1202 |
+
"model.layers.32.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1203 |
+
"model.layers.32.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1204 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1205 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 1206 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 1207 |
+
"model.layers.32.self_attn.k_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1208 |
+
"model.layers.32.self_attn.k_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1209 |
+
"model.layers.32.self_attn.k_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1210 |
+
"model.layers.32.self_attn.k_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1211 |
+
"model.layers.32.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1212 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 1213 |
+
"model.layers.32.self_attn.o_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1214 |
+
"model.layers.32.self_attn.o_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1215 |
+
"model.layers.32.self_attn.o_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1216 |
+
"model.layers.32.self_attn.o_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1217 |
+
"model.layers.32.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1218 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 1219 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 1220 |
+
"model.layers.32.self_attn.q_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1221 |
+
"model.layers.32.self_attn.q_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1222 |
+
"model.layers.32.self_attn.q_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1223 |
+
"model.layers.32.self_attn.q_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1224 |
+
"model.layers.32.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1225 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 1226 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 1227 |
+
"model.layers.32.self_attn.v_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1228 |
+
"model.layers.32.self_attn.v_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1229 |
+
"model.layers.32.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1230 |
+
"model.layers.32.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1231 |
+
"model.layers.32.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1232 |
+
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1233 |
+
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1234 |
+
"model.layers.33.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1235 |
+
"model.layers.33.mlp.down_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1236 |
+
"model.layers.33.mlp.down_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1237 |
+
"model.layers.33.mlp.down_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1238 |
+
"model.layers.33.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1239 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 1240 |
+
"model.layers.33.mlp.gate_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1241 |
+
"model.layers.33.mlp.gate_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1242 |
+
"model.layers.33.mlp.gate_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1243 |
+
"model.layers.33.mlp.gate_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1244 |
+
"model.layers.33.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1245 |
+
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 1246 |
+
"model.layers.33.mlp.up_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1247 |
+
"model.layers.33.mlp.up_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1248 |
+
"model.layers.33.mlp.up_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1249 |
+
"model.layers.33.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1250 |
+
"model.layers.33.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1251 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1252 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 1253 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 1254 |
+
"model.layers.33.self_attn.k_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1255 |
+
"model.layers.33.self_attn.k_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1256 |
+
"model.layers.33.self_attn.k_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1257 |
+
"model.layers.33.self_attn.k_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1258 |
+
"model.layers.33.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1259 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 1260 |
+
"model.layers.33.self_attn.o_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1261 |
+
"model.layers.33.self_attn.o_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1262 |
+
"model.layers.33.self_attn.o_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1263 |
+
"model.layers.33.self_attn.o_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1264 |
+
"model.layers.33.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1265 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 1266 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 1267 |
+
"model.layers.33.self_attn.q_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1268 |
+
"model.layers.33.self_attn.q_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1269 |
+
"model.layers.33.self_attn.q_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1270 |
+
"model.layers.33.self_attn.q_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1271 |
+
"model.layers.33.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1272 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 1273 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 1274 |
+
"model.layers.33.self_attn.v_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1275 |
+
"model.layers.33.self_attn.v_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1276 |
+
"model.layers.33.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1277 |
+
"model.layers.33.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1278 |
+
"model.layers.33.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1279 |
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1280 |
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1281 |
"model.layers.34.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
|
|
|
| 1283 |
"model.layers.34.mlp.down_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1284 |
"model.layers.34.mlp.down_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1285 |
"model.layers.34.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1286 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 1287 |
+
"model.layers.34.mlp.gate_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1288 |
+
"model.layers.34.mlp.gate_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1289 |
+
"model.layers.34.mlp.gate_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1290 |
+
"model.layers.34.mlp.gate_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1291 |
+
"model.layers.34.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1292 |
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 1293 |
"model.layers.34.mlp.up_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1294 |
"model.layers.34.mlp.up_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
|
|
|
| 1296 |
"model.layers.34.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1297 |
"model.layers.34.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1298 |
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1299 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 1300 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 1301 |
+
"model.layers.34.self_attn.k_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1302 |
+
"model.layers.34.self_attn.k_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1303 |
+
"model.layers.34.self_attn.k_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1304 |
+
"model.layers.34.self_attn.k_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1305 |
+
"model.layers.34.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1306 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 1307 |
+
"model.layers.34.self_attn.o_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1308 |
+
"model.layers.34.self_attn.o_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1309 |
+
"model.layers.34.self_attn.o_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1310 |
+
"model.layers.34.self_attn.o_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1311 |
+
"model.layers.34.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1312 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 1313 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 1314 |
+
"model.layers.34.self_attn.q_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1315 |
+
"model.layers.34.self_attn.q_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1316 |
+
"model.layers.34.self_attn.q_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1317 |
+
"model.layers.34.self_attn.q_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1318 |
+
"model.layers.34.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1319 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 1320 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 1321 |
+
"model.layers.34.self_attn.v_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 1322 |
+
"model.layers.34.self_attn.v_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
| 1323 |
+
"model.layers.34.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 1324 |
+
"model.layers.34.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 1325 |
+
"model.layers.34.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 1326 |
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 1327 |
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 1328 |
"model.layers.35.mlp.down_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
|
|
|
| 2075 |
"model.layers.49.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2076 |
"model.layers.49.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2077 |
"model.layers.49.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2078 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2079 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2080 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2081 |
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 2082 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2083 |
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
| 2084 |
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2085 |
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2086 |
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 2087 |
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2088 |
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 2089 |
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 2090 |
+
"model.layers.50.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2091 |
+
"model.layers.50.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2092 |
+
"model.layers.50.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2093 |
+
"model.layers.50.mlp.down_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2094 |
+
"model.layers.50.mlp.down_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2095 |
+
"model.layers.50.mlp.down_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2096 |
+
"model.layers.50.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2097 |
"model.layers.50.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 2098 |
"model.layers.50.mlp.gate_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
| 2099 |
"model.layers.50.mlp.gate_proj.weight.nested_absmax": "model-00004-of-00005.safetensors",
|
|
|
|
| 2106 |
"model.layers.50.mlp.up_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2107 |
"model.layers.50.mlp.up_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2108 |
"model.layers.50.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2109 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2110 |
"model.layers.50.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 2111 |
"model.layers.50.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 2112 |
"model.layers.50.self_attn.k_proj.weight.absmax": "model-00004-of-00005.safetensors",
|
|
|
|
| 2134 |
"model.layers.50.self_attn.v_proj.weight.nested_quant_map": "model-00004-of-00005.safetensors",
|
| 2135 |
"model.layers.50.self_attn.v_proj.weight.quant_map": "model-00004-of-00005.safetensors",
|
| 2136 |
"model.layers.50.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00004-of-00005.safetensors",
|
| 2137 |
+
"model.layers.51.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2138 |
+
"model.layers.51.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2139 |
+
"model.layers.51.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2140 |
+
"model.layers.51.mlp.down_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2141 |
+
"model.layers.51.mlp.down_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2142 |
+
"model.layers.51.mlp.down_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2143 |
+
"model.layers.51.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2144 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 2145 |
+
"model.layers.51.mlp.gate_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2146 |
+
"model.layers.51.mlp.gate_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2147 |
+
"model.layers.51.mlp.gate_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2148 |
+
"model.layers.51.mlp.gate_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2149 |
+
"model.layers.51.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2150 |
+
"model.layers.51.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 2151 |
+
"model.layers.51.mlp.up_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2152 |
+
"model.layers.51.mlp.up_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2153 |
+
"model.layers.51.mlp.up_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2154 |
+
"model.layers.51.mlp.up_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2155 |
+
"model.layers.51.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2156 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2157 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
|
| 2158 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 2159 |
+
"model.layers.51.self_attn.k_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2160 |
+
"model.layers.51.self_attn.k_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2161 |
+
"model.layers.51.self_attn.k_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2162 |
+
"model.layers.51.self_attn.k_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2163 |
+
"model.layers.51.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2164 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 2165 |
+
"model.layers.51.self_attn.o_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2166 |
+
"model.layers.51.self_attn.o_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2167 |
+
"model.layers.51.self_attn.o_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2168 |
+
"model.layers.51.self_attn.o_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2169 |
+
"model.layers.51.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2170 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
|
| 2171 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 2172 |
+
"model.layers.51.self_attn.q_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2173 |
+
"model.layers.51.self_attn.q_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2174 |
+
"model.layers.51.self_attn.q_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2175 |
+
"model.layers.51.self_attn.q_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2176 |
+
"model.layers.51.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2177 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
|
| 2178 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 2179 |
+
"model.layers.51.self_attn.v_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2180 |
+
"model.layers.51.self_attn.v_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2181 |
+
"model.layers.51.self_attn.v_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2182 |
+
"model.layers.51.self_attn.v_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2183 |
+
"model.layers.51.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2184 |
+
"model.layers.52.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2185 |
+
"model.layers.52.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2186 |
+
"model.layers.52.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2187 |
+
"model.layers.52.mlp.down_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2188 |
+
"model.layers.52.mlp.down_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2189 |
+
"model.layers.52.mlp.down_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2190 |
+
"model.layers.52.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2191 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 2192 |
+
"model.layers.52.mlp.gate_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2193 |
+
"model.layers.52.mlp.gate_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2194 |
+
"model.layers.52.mlp.gate_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2195 |
+
"model.layers.52.mlp.gate_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2196 |
+
"model.layers.52.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2197 |
+
"model.layers.52.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 2198 |
+
"model.layers.52.mlp.up_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2199 |
+
"model.layers.52.mlp.up_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2200 |
+
"model.layers.52.mlp.up_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2201 |
+
"model.layers.52.mlp.up_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2202 |
+
"model.layers.52.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2203 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2204 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
|
| 2205 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 2206 |
+
"model.layers.52.self_attn.k_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2207 |
+
"model.layers.52.self_attn.k_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2208 |
+
"model.layers.52.self_attn.k_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2209 |
+
"model.layers.52.self_attn.k_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2210 |
+
"model.layers.52.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2211 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 2212 |
+
"model.layers.52.self_attn.o_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2213 |
+
"model.layers.52.self_attn.o_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2214 |
+
"model.layers.52.self_attn.o_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2215 |
+
"model.layers.52.self_attn.o_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2216 |
+
"model.layers.52.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2217 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
|
| 2218 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 2219 |
+
"model.layers.52.self_attn.q_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2220 |
+
"model.layers.52.self_attn.q_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2221 |
+
"model.layers.52.self_attn.q_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2222 |
+
"model.layers.52.self_attn.q_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2223 |
+
"model.layers.52.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2224 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
|
| 2225 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 2226 |
+
"model.layers.52.self_attn.v_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2227 |
+
"model.layers.52.self_attn.v_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2228 |
+
"model.layers.52.self_attn.v_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2229 |
+
"model.layers.52.self_attn.v_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2230 |
+
"model.layers.52.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2231 |
+
"model.layers.53.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2232 |
+
"model.layers.53.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2233 |
+
"model.layers.53.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2234 |
+
"model.layers.53.mlp.down_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2235 |
+
"model.layers.53.mlp.down_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2236 |
+
"model.layers.53.mlp.down_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2237 |
+
"model.layers.53.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2238 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 2239 |
+
"model.layers.53.mlp.gate_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2240 |
+
"model.layers.53.mlp.gate_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2241 |
+
"model.layers.53.mlp.gate_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2242 |
+
"model.layers.53.mlp.gate_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2243 |
+
"model.layers.53.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2244 |
+
"model.layers.53.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 2245 |
+
"model.layers.53.mlp.up_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2246 |
+
"model.layers.53.mlp.up_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2247 |
+
"model.layers.53.mlp.up_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2248 |
+
"model.layers.53.mlp.up_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2249 |
+
"model.layers.53.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2250 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2251 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
|
| 2252 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 2253 |
+
"model.layers.53.self_attn.k_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2254 |
+
"model.layers.53.self_attn.k_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2255 |
+
"model.layers.53.self_attn.k_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2256 |
+
"model.layers.53.self_attn.k_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2257 |
+
"model.layers.53.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2258 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 2259 |
+
"model.layers.53.self_attn.o_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2260 |
+
"model.layers.53.self_attn.o_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2261 |
+
"model.layers.53.self_attn.o_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2262 |
+
"model.layers.53.self_attn.o_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2263 |
+
"model.layers.53.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2264 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
|
| 2265 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 2266 |
+
"model.layers.53.self_attn.q_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2267 |
+
"model.layers.53.self_attn.q_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2268 |
+
"model.layers.53.self_attn.q_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2269 |
+
"model.layers.53.self_attn.q_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2270 |
+
"model.layers.53.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2271 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
|
| 2272 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 2273 |
+
"model.layers.53.self_attn.v_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2274 |
+
"model.layers.53.self_attn.v_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2275 |
+
"model.layers.53.self_attn.v_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2276 |
+
"model.layers.53.self_attn.v_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2277 |
+
"model.layers.53.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2278 |
"model.layers.54.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2279 |
"model.layers.54.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2280 |
"model.layers.54.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
|
|
|
| 2295 |
"model.layers.54.mlp.up_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2296 |
"model.layers.54.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2297 |
"model.layers.54.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2298 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
|
| 2299 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 2300 |
+
"model.layers.54.self_attn.k_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2301 |
+
"model.layers.54.self_attn.k_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2302 |
+
"model.layers.54.self_attn.k_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2303 |
+
"model.layers.54.self_attn.k_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2304 |
+
"model.layers.54.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2305 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 2306 |
+
"model.layers.54.self_attn.o_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2307 |
+
"model.layers.54.self_attn.o_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2308 |
+
"model.layers.54.self_attn.o_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2309 |
+
"model.layers.54.self_attn.o_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2310 |
+
"model.layers.54.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2311 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
|
| 2312 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 2313 |
+
"model.layers.54.self_attn.q_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2314 |
+
"model.layers.54.self_attn.q_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2315 |
+
"model.layers.54.self_attn.q_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2316 |
+
"model.layers.54.self_attn.q_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2317 |
+
"model.layers.54.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2318 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
|
| 2319 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 2320 |
+
"model.layers.54.self_attn.v_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
| 2321 |
+
"model.layers.54.self_attn.v_proj.weight.nested_absmax": "model-00005-of-00005.safetensors",
|
| 2322 |
+
"model.layers.54.self_attn.v_proj.weight.nested_quant_map": "model-00005-of-00005.safetensors",
|
| 2323 |
+
"model.layers.54.self_attn.v_proj.weight.quant_map": "model-00005-of-00005.safetensors",
|
| 2324 |
+
"model.layers.54.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2325 |
"model.layers.55.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2326 |
"model.layers.55.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2327 |
"model.layers.55.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
|
|
|
| 2559 |
"model.layers.59.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2560 |
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2561 |
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 2562 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 2563 |
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 2564 |
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2565 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 2566 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 2567 |
+
"model.layers.6.self_attn.k_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2568 |
+
"model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2569 |
+
"model.layers.6.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2570 |
+
"model.layers.6.self_attn.k_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2571 |
+
"model.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2572 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 2573 |
+
"model.layers.6.self_attn.o_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2574 |
+
"model.layers.6.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2575 |
+
"model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2576 |
+
"model.layers.6.self_attn.o_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2577 |
+
"model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2578 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 2579 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 2580 |
+
"model.layers.6.self_attn.q_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2581 |
+
"model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2582 |
+
"model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2583 |
+
"model.layers.6.self_attn.q_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2584 |
+
"model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2585 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 2586 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 2587 |
+
"model.layers.6.self_attn.v_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2588 |
+
"model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2589 |
+
"model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2590 |
+
"model.layers.6.self_attn.v_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2591 |
+
"model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2592 |
"model.layers.60.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 2593 |
"model.layers.60.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 2594 |
"model.layers.60.mlp.down_proj.weight.absmax": "model-00005-of-00005.safetensors",
|
|
|
|
| 2779 |
"model.layers.63.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00005-of-00005.safetensors",
|
| 2780 |
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2781 |
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 2782 |
+
"model.layers.7.mlp.down_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2783 |
+
"model.layers.7.mlp.down_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2784 |
+
"model.layers.7.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2785 |
+
"model.layers.7.mlp.down_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2786 |
+
"model.layers.7.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2787 |
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 2788 |
+
"model.layers.7.mlp.gate_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2789 |
+
"model.layers.7.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2790 |
+
"model.layers.7.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2791 |
+
"model.layers.7.mlp.gate_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2792 |
+
"model.layers.7.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2793 |
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 2794 |
+
"model.layers.7.mlp.up_proj.weight.absmax": "model-00002-of-00005.safetensors",
|
| 2795 |
+
"model.layers.7.mlp.up_proj.weight.nested_absmax": "model-00002-of-00005.safetensors",
|
| 2796 |
+
"model.layers.7.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00005.safetensors",
|
| 2797 |
+
"model.layers.7.mlp.up_proj.weight.quant_map": "model-00002-of-00005.safetensors",
|
| 2798 |
+
"model.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2799 |
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2800 |
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 2801 |
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
| 2826 |
"model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00005.safetensors",
|
| 2827 |
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2828 |
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2829 |
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2830 |
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2831 |
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 2832 |
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 2833 |
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
tokenizer_config.json
CHANGED
|
@@ -195,16 +195,16 @@
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
-
"model_max_length":
|
| 204 |
"pad_token": "<|vision_pad|>",
|
| 205 |
"padding_side": "left",
|
| 206 |
"processor_class": "Qwen2_5_VLProcessor",
|
| 207 |
"split_special_tokens": false,
|
| 208 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 209 |
-
"unk_token": null
|
| 210 |
-
}
|
|
|
|
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
|
|
|
| 198 |
"clean_up_tokenization_spaces": false,
|
| 199 |
"eos_token": "<|im_end|>",
|
| 200 |
"errors": "replace",
|
| 201 |
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 128000,
|
| 203 |
"pad_token": "<|vision_pad|>",
|
| 204 |
"padding_side": "left",
|
| 205 |
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
"split_special_tokens": false,
|
| 207 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null,
|
| 209 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 210 |
+
}
|