Hugging Face's logo

nvidia
/
Llama-3.1-70B-Instruct-FP8

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
zhiyucheng commited on
Commit
2c5231c
·
1 Parent(s): 20af8c9

update

Browse files
Files changed (22) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
  3. hf_quant_config.json +5 -2
  4. model-00001-of-00015.safetensors +2 -2
  5. model-00002-of-00015.safetensors +2 -2
  6. model-00003-of-00015.safetensors +2 -2
  7. model-00004-of-00015.safetensors +2 -2
  8. model-00005-of-00015.safetensors +2 -2
  9. model-00006-of-00015.safetensors +2 -2
  10. model-00007-of-00015.safetensors +2 -2
  11. model-00008-of-00015.safetensors +2 -2
  12. model-00009-of-00015.safetensors +2 -2
  13. model-00010-of-00015.safetensors +2 -2
  14. model-00011-of-00015.safetensors +2 -2
  15. model-00012-of-00015.safetensors +2 -2
  16. model-00013-of-00015.safetensors +2 -2
  17. model-00014-of-00015.safetensors +2 -2
  18. model-00015-of-00015.safetensors +2 -2
  19. model.safetensors.index.json +0 -0
  20. special_tokens_map.json +0 -0
  21. tokenizer.json +0 -0
  22. tokenizer_config.json +1 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/opt/llama3.1/Meta-Llama-3.1-70B-Instruct/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -33,7 +33,7 @@
33
  "rope_theta": 500000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "bfloat16",
36
- "transformers_version": "4.43.4",
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
 
1
  {
2
+ "_name_or_path": "/opt/zhiyu_hf_ckpts/Llama-3.1-70B-Instruct/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
33
  "rope_theta": 500000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.44.0",
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
generation_config.json CHANGED
@@ -8,5 +8,5 @@
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
- "transformers_version": "4.43.4"
12
  }
 
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
+ "transformers_version": "4.44.0"
12
  }
hf_quant_config.json CHANGED
@@ -1,10 +1,13 @@
1
  {
2
  "producer": {
3
  "name": "modelopt",
4
- "version": "0.17.0"
5
  },
6
  "quantization": {
7
  "quant_algo": "FP8",
8
- "kv_cache_quant_algo": null
 
 
 
9
  }
10
  }
 
1
  {
2
  "producer": {
3
  "name": "modelopt",
4
+ "version": "0.23.0"
5
  },
6
  "quantization": {
7
  "quant_algo": "FP8",
8
+ "kv_cache_quant_algo": "FP8",
9
+ "exclude_modules": [
10
+ "lm_head"
11
+ ]
12
  }
13
  }
model-00001-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bead031168838510de9264aeda325655628067f19b0af87316f56b231558b0e4
3
- size 4819362416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21fea9c05ad6e00434f3fb73d778d18bb594ac3a7a7bea1a978160227c881a5
3
+ size 4819363200
model-00002-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ae1869d8e92a3cca5cf68b64cd77ab58e4d94f1164e2d85ed2f04dfbecd33dd
3
- size 4983043184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff18d0fe3c6233c256347080b18a41f8ab1a84ab2954d8d8492f5b1f1cb204a0
3
+ size 4983044160
model-00003-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15eb61237d6a1f1447627885774ff49ef5cddfaa729cca2f99f15cfe32c35756
3
- size 4899125208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e61982a1e76fcab453d8318ee1e63c3b8c68b979c86e6a3b0d737db0137a3fa
3
+ size 4899126392
model-00004-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae7b10113024fcb0e2409bcb2260f292c3ed50d95b87e86728a1aa2a6234d4cd
3
- size 4899158224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8443516c25f10fba4ea56ef1103bcd53544f8f7b1207476d70824912d5e2685
3
+ size 4899159416
model-00005-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fffed5cf848d446082f9725ca289603607fc8eb7a27870e7494e5575ddba31b2
3
- size 4899158224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5393156ffbbd9ad3b2a04be5392fd6107b1a734fd8434f2ff9fa989f90ca437
3
+ size 4899159408
model-00006-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc8686f61bdaebcfef375c8d938994ce1a7fb21049dd808201927cffcc43573
3
- size 4983043312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a00c83e264c731d4923f7b24bc91f9a2b992472fd524ebde77d7113cdb7b20b
3
+ size 4983044296
model-00007-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92d2f2d86a057fa8c34d9aff5d2f26d7df6cbc46a1d4a00dbafd325659d32969
3
- size 4899125232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf43539ab4ea597ef9759881678942bf8585087121496142eabd0d83cd6bd4f6
3
+ size 4899126416
model-00008-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc22f3cc00ed3e0065938766ce2e01ec9001120df62ec50fff20d39c04fade4b
3
- size 4899158224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a5f7e53270acc9d9e35469aa4eb9fe17e743779be0b8e1569ca45f17f6e391d
3
+ size 4899159416
model-00009-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da2a651a2e0905097f2099785a190e2e252cba66d5c6612d5491e3fca2f5a58a
3
- size 4899158224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63120d51e50173d75346ba6ef04844d824b5a28a9175dc9001348dff44406557
3
+ size 4899159408
model-00010-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:540ac3259424692ce88d715531e08aefaf5a4d83d120e180789aaf9cdb09336a
3
- size 4983043312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9412ea51371da7a4b1478f347b8274ccadb42d5ca4e83a4af5296c346a862eb4
3
+ size 4983044296
model-00011-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09137ef45bf08256b5c314958311898f2cce248c1fe52b9b6091c9fd83e70d8e
3
- size 4899125232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4f754147e4ad7ce436fb5443df6c0b7b36726495f340bcd133ed42dec4d1a9
3
+ size 4899126416
model-00012-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:942ef3e4fe3e3eaf254709968deedd269e32455a269e8eeb8655d5033352286f
3
- size 4899158224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ec8ec1cb4d4bfe9bf55870ec3d77b22a9a88ff0eeff428b6141f7907552edc
3
+ size 4899159416
model-00013-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46aae257c9c13e45c51cf8390f3ad1e30206b5530243fc246e8bebaf0953de01
3
- size 4899158224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de8cbec0025d4b86f77060d1cef452a3316c6f61f6c7d3ece01654bd2ae41ce
3
+ size 4899159408
model-00014-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cbca29b0cd77ceb3f9fa92b4ca0019ef69f93da0bda3ca8c75bb684c44da677
3
- size 4983043312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:047841a4f0e868ed1715617b8e35729945e45bc477d3a8f2ddfa479f070d3375
3
+ size 4983044296
model-00015-of-00015.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24a996c6c865f39e5301a1dc151bc772483d587d3815d378bf1efa252490aa00
3
- size 3812709424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c430f7ce602a4e4ef70e94baed4b012837903565f7c09c3af40194896ef138a
3
+ size 3812709816
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
File without changes
tokenizer.json CHANGED
File without changes
tokenizer_config.json CHANGED
@@ -2058,5 +2058,6 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }