Hugging Face's logo

tensorblock
/
karakuri-lm-32b-thinking-2501-exp-GGUF

Transformers
GGUF
English
Japanese
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
a6007ce
ยท
verified ยท
1 Parent(s): c961bff

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +84 -0
  3. karakuri-lm-32b-thinking-2501-exp-Q2_K.gguf +3 -0
  4. karakuri-lm-32b-thinking-2501-exp-Q3_K_L.gguf +3 -0
  5. karakuri-lm-32b-thinking-2501-exp-Q3_K_M.gguf +3 -0
  6. karakuri-lm-32b-thinking-2501-exp-Q3_K_S.gguf +3 -0
  7. karakuri-lm-32b-thinking-2501-exp-Q4_0.gguf +3 -0
  8. karakuri-lm-32b-thinking-2501-exp-Q4_K_M.gguf +3 -0
  9. karakuri-lm-32b-thinking-2501-exp-Q4_K_S.gguf +3 -0
  10. karakuri-lm-32b-thinking-2501-exp-Q5_0.gguf +3 -0
  11. karakuri-lm-32b-thinking-2501-exp-Q5_K_M.gguf +3 -0
  12. karakuri-lm-32b-thinking-2501-exp-Q5_K_S.gguf +3 -0
  13. karakuri-lm-32b-thinking-2501-exp-Q6_K.gguf +3 -0
  14. karakuri-lm-32b-thinking-2501-exp-Q8_0.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ karakuri-lm-32b-thinking-2501-exp-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ karakuri-lm-32b-thinking-2501-exp-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ karakuri-lm-32b-thinking-2501-exp-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ karakuri-lm-32b-thinking-2501-exp-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ karakuri-lm-32b-thinking-2501-exp-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ karakuri-lm-32b-thinking-2501-exp-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ karakuri-lm-32b-thinking-2501-exp-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ karakuri-lm-32b-thinking-2501-exp-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ karakuri-lm-32b-thinking-2501-exp-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ karakuri-lm-32b-thinking-2501-exp-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ karakuri-lm-32b-thinking-2501-exp-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ karakuri-lm-32b-thinking-2501-exp-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ language:
5
+ - en
6
+ - ja
7
+ base_model: karakuri-ai/karakuri-lm-32b-thinking-2501-exp
8
+ tags:
9
+ - TensorBlock
10
+ - GGUF
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## karakuri-ai/karakuri-lm-32b-thinking-2501-exp - GGUF
25
+
26
+ This repo contains GGUF format model files for [karakuri-ai/karakuri-lm-32b-thinking-2501-exp](https://huggingface.co/karakuri-ai/karakuri-lm-32b-thinking-2501-exp).
27
+
28
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4882](https://github.com/ggml-org/llama.cpp/commit/be7c3034108473beda214fd1d7c98fd6a7a3bdf5).
29
+
30
+ <div style="text-align: left; margin: 20px 0;">
31
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
32
+ Run them on the TensorBlock client using your local machine โ†—
33
+ </a>
34
+ </div>
35
+
36
+ ## Prompt template
37
+
38
+ ```
39
+ <|im_start|>system
40
+ {system_prompt}<|im_end|>
41
+ <|im_start|>user
42
+ {prompt}<|im_end|>
43
+ <|im_start|>assistant
44
+ ```
45
+
46
+ ## Model file specification
47
+
48
+ | Filename | Quant type | File Size | Description |
49
+ | -------- | ---------- | --------- | ----------- |
50
+ | [karakuri-lm-32b-thinking-2501-exp-Q2_K.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
51
+ | [karakuri-lm-32b-thinking-2501-exp-Q3_K_S.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
52
+ | [karakuri-lm-32b-thinking-2501-exp-Q3_K_M.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
53
+ | [karakuri-lm-32b-thinking-2501-exp-Q3_K_L.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
54
+ | [karakuri-lm-32b-thinking-2501-exp-Q4_0.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
55
+ | [karakuri-lm-32b-thinking-2501-exp-Q4_K_S.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
56
+ | [karakuri-lm-32b-thinking-2501-exp-Q4_K_M.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
57
+ | [karakuri-lm-32b-thinking-2501-exp-Q5_0.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
58
+ | [karakuri-lm-32b-thinking-2501-exp-Q5_K_S.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
59
+ | [karakuri-lm-32b-thinking-2501-exp-Q5_K_M.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
60
+ | [karakuri-lm-32b-thinking-2501-exp-Q6_K.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
61
+ | [karakuri-lm-32b-thinking-2501-exp-Q8_0.gguf](https://huggingface.co/tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF/blob/main/karakuri-lm-32b-thinking-2501-exp-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
62
+
63
+
64
+ ## Downloading instruction
65
+
66
+ ### Command line
67
+
68
+ Firstly, install Huggingface Client
69
+
70
+ ```shell
71
+ pip install -U "huggingface_hub[cli]"
72
+ ```
73
+
74
+ Then, downoad the individual model file the a local directory
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF --include "karakuri-lm-32b-thinking-2501-exp-Q2_K.gguf" --local-dir MY_LOCAL_DIR
78
+ ```
79
+
80
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
81
+
82
+ ```shell
83
+ huggingface-cli download tensorblock/karakuri-lm-32b-thinking-2501-exp-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
84
+ ```
karakuri-lm-32b-thinking-2501-exp-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b09d3db7765add58210aa64cd1928d3846beb3e153cf6003d9d8f78bede2257
3
+ size 12313100928
karakuri-lm-32b-thinking-2501-exp-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3212acc91dc3bad5c3804d0e47045f048bdb558a63ad4df068c8dbb668058a43
3
+ size 17247081088
karakuri-lm-32b-thinking-2501-exp-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc6b8c19152b6c29404d96417eeccdde5b2f2e1fc1908e14166ce0f4655bf7c
3
+ size 15935050368
karakuri-lm-32b-thinking-2501-exp-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7044a11cdaa1345378809c27b89e60f5231ac4e3d471f4d639a05d5d3971fd
3
+ size 14392332928
karakuri-lm-32b-thinking-2501-exp-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da82fbadffede9a43b6bed583452fe20212e08669575d0f9c19b97e31fc1932b
3
+ size 18640233088
karakuri-lm-32b-thinking-2501-exp-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc98ed6afb8a56f9a3961afc5111c7e6a5961d8aed571425846e9cc8451c872
3
+ size 19851338368
karakuri-lm-32b-thinking-2501-exp-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d434b2fc6ead693886da224e571986af1116999b4c7cf93539093f09802d1d
3
+ size 18784412288
karakuri-lm-32b-thinking-2501-exp-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23e8d5321feef400d82ff09030cfdde6348ff4368bc98c9db2e36866f094ef6
3
+ size 22638256768
karakuri-lm-32b-thinking-2501-exp-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7dcaa8f84facac4192d682d3d89fb3318738679fa007420f3f79d3c6c2f36a
3
+ size 23262159488
karakuri-lm-32b-thinking-2501-exp-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67586265326fd7015d5f455adc2de8f8281c94437a5fae23f7359fd01750155d
3
+ size 22638256768
karakuri-lm-32b-thinking-2501-exp-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6a01e1d4c4f9dc25719087a62a7882aa0599072cd8d0126f2f754a63aa573e
3
+ size 26886156928
karakuri-lm-32b-thinking-2501-exp-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a5f0d3535ef13e3dee067a540fcf65dba36a5c3291032df4b5df162cf5be41
3
+ size 34820887168