Hugging Face's logo

VPTQ-community
/
Qwen2.5-72B-Instruct-v8-k65536-4-woft

Safetensors
qwen2
VPTQ
Quantized
Quantization
vptq
Model card Files
xet
Community
1
OpenSourceRonin commited on
Commit
dd16736
·
verified ·
1 Parent(s): 8941c86

Upload Qwen2.5-72B-Instruct-v8-k65536-4-woft model

Browse files
Files changed (9) hide show
  1. config.json +0 -0
  2. generation_config.json +3 -15
  3. model-00001-of-00006.safetensors +2 -2
  4. model-00002-of-00006.safetensors +2 -2
  5. model-00003-of-00006.safetensors +2 -2
  6. model-00004-of-00006.safetensors +2 -2
  7. model-00005-of-00006.safetensors +2 -2
  8. model.safetensors.index.json +0 -0
  9. tokenizer_config.json +1 -0
config.json CHANGED
The diff for this file is too large to render. See raw diff
 
generation_config.json CHANGED
@@ -1,18 +1,6 @@
1
  {
2
- "attn_implementation": "flash_attention_2",
3
  "bos_token_id": 151643,
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 151645,
7
- 151643
8
- ],
9
- "num_assistant_tokens": 5,
10
- "num_assistant_tokens_schedule": "heuristic",
11
- "pad_token_id": 151643,
12
- "repetition_penalty": 1.05,
13
- "return_legacy_cache": true,
14
- "temperature": 0.7,
15
- "top_k": 20,
16
- "top_p": 0.8,
17
- "transformers_version": "4.45.1"
18
  }
 
1
  {
2
+ "_from_model_config": true,
3
  "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.49.0"
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f8e8807e1d980d69ead3f3bdc06edde23fb56151f7062bb50746d237df77276
3
- size 4969338928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2f418039b2ee586263b6391a6f7370efe234356a30a5d643369785e013f1fe
3
+ size 4967756992
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:107a9d250b8463e2d9812cd8941a509332fb36a324a04de2d414c5357e4abae2
3
- size 4955684208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0a1a43c1e46d43dd3e2c39263dccd63b998becff1fc5d98fe6f017eaec3a4b
3
+ size 4952595944
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0c8bd0c33b9237159162c5bf0bb3cd730f2a2125362d58d4aecdf4d9ae25bc9
3
- size 4978120448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f080de545c845ce63b143b4696ef639dead9ddd2a79528a611e524cd6448f448
3
+ size 4975038912
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9505045c8585e5af8795510a1e117215423930b311b03f689a52272ca119305b
3
- size 4955684224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be9beb5d6e3a2b767f021252da36a53d871685976eead87fa142285d6b5b30d
3
+ size 4952595960
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31c62116d004ce261035b34224febdcd296ecf0db672d5714dc8dc3ef155e867
3
- size 3009640072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a176e7ba74af0d751c5a9c01908aa06c885302fbd72aff6058fca08ec502fbb
3
+ size 3007824136
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -199,6 +199,7 @@
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|im_end|>",
201
  "errors": "replace",
 
202
  "legacy": false,
203
  "model_max_length": 131072,
204
  "pad_token": "<|endoftext|>",
 
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|im_end|>",
201
  "errors": "replace",
202
+ "extra_special_tokens": {},
203
  "legacy": false,
204
  "model_max_length": 131072,
205
  "pad_token": "<|endoftext|>",