Hugging Face's logo

VPTQ-community
/
Qwen2.5-72B-Instruct-v8-k65536-256-woft

Safetensors
qwen2
VPTQ
Quantized
Quantization
vptq
Model card Files
xet
Community
2
OpenSourceRonin commited on
Commit
796966e
·
verified ·
1 Parent(s): c587994

Upload Qwen2.5-72B-Instruct-v8-k65536-256-woft model

Browse files
Files changed (10) hide show
  1. config.json +0 -0
  2. generation_config.json +3 -15
  3. model-00001-of-00007.safetensors +2 -2
  4. model-00002-of-00007.safetensors +2 -2
  5. model-00003-of-00007.safetensors +2 -2
  6. model-00004-of-00007.safetensors +2 -2
  7. model-00005-of-00007.safetensors +2 -2
  8. model-00006-of-00007.safetensors +2 -2
  9. model.safetensors.index.json +0 -0
  10. 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-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcb777d1f2573f818fb2889137c1459a3bf0ce01d35ba4b3d97ef4d35c03cda5
3
- size 4911671296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1cca9ac68c3072ef7dcd5f1addc80111a61f1b79cd2440d6367affbd41b09e
3
+ size 4910481480
model-00002-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d80bb8668e4f11f608abadc2b43c66de623b967304095ac0825ae0849d71404a
3
- size 4994286688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06bee559aec4c9ceb85639ffffaac140a946e1a19513565a75a60a81001ae12
3
+ size 4991979672
model-00003-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9183b503f96602973afcbeaec698e36f5480c0651e88ade8167415f73dddcc52
3
- size 4963339464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7d4aead2090b07d3b485899a1573ae11553093b89b9bf4fc839399932ed59f
3
+ size 4960982960
model-00004-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf4601f4e79465f5147575c33642fb9d87e627bad48f8eae8391fd0a8fc3d55e
3
- size 4963260728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c7af38cece3fc9ece12c3cf7aa0ecf7f02e07bbef65e6ad617b74177d37656
3
+ size 4960946968
model-00005-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:503d48670d0aa690dc1fd4c8c031db48fd3640ce6b0b42be45fb687773d15425
3
- size 4963388984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753f8b0aa72b819c78973de4dd2571c6d6547a6e59648b738d0198526e37badc
3
+ size 4961032472
model-00006-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64c9c685448b9e7684ede54bc2fa64994c25d6a72be9049f2582e1c881967917
3
- size 4657215656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaaad556d5058f00ce22902a71cb9347284447646a8591fc6b877ff2f89553cf
3
+ size 4655083328
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|>",