OpenSourceRonin commited on
Commit
04a0b7f
1 Parent(s): 276310e

Upload model Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. README.md +11 -11
  3. config.json +1 -1
  4. generation_config.json +4 -1
  5. tokenizer.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,7 +1,7 @@
 
1
  ---
2
  license: llama3.1
3
  ---
4
-
5
  **Disclaimer**:
6
 
7
  The model is reproduced based on the paper *VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models* [github](https://github.com/microsoft/vptq) and [arXiv](https://arxiv.org/abs/2409.17066)
@@ -18,14 +18,14 @@ The PPL test results are for reference only and were collected using GPTQ testin
18
 
19
  ```json
20
  {
21
- "ctx_2048": {
22
- "wikitext2": 7.414072513580322
23
- },
24
- "ctx_4096": {
25
- "wikitext2": 6.940601348876953
26
- },
27
- "ctx_8192": {
28
- "wikitext2": 6.678436756134033
29
- }
30
  }
31
- ```
 
1
+
2
  ---
3
  license: llama3.1
4
  ---
 
5
  **Disclaimer**:
6
 
7
  The model is reproduced based on the paper *VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models* [github](https://github.com/microsoft/vptq) and [arXiv](https://arxiv.org/abs/2409.17066)
 
18
 
19
  ```json
20
  {
21
+ "ctx_2048": {
22
+ "wikitext2": 7.414072513580322
23
+ },
24
+ "ctx_4096": {
25
+ "wikitext2": 6.940601348876953
26
+ },
27
+ "ctx_8192": {
28
+ "wikitext2": 6.678436756134033
29
+ }
30
  }
31
+ ```
config.json CHANGED
@@ -5411,7 +5411,7 @@
5411
  "rope_theta": 500000.0,
5412
  "tie_word_embeddings": false,
5413
  "torch_dtype": "bfloat16",
5414
- "transformers_version": "4.44.2",
5415
  "use_cache": true,
5416
  "vocab_size": 128256
5417
  }
 
5411
  "rope_theta": 500000.0,
5412
  "tie_word_embeddings": false,
5413
  "torch_dtype": "bfloat16",
5414
+ "transformers_version": "4.45.1",
5415
  "use_cache": true,
5416
  "vocab_size": 128256
5417
  }
generation_config.json CHANGED
@@ -7,7 +7,10 @@
7
  128008,
8
  128009
9
  ],
 
 
 
10
  "temperature": 0.6,
11
  "top_p": 0.9,
12
- "transformers_version": "4.44.2"
13
  }
 
7
  128008,
8
  128009
9
  ],
10
+ "num_assistant_tokens": 5,
11
+ "num_assistant_tokens_schedule": "heuristic",
12
+ "return_legacy_cache": true,
13
  "temperature": 0.6,
14
  "top_p": 0.9,
15
+ "transformers_version": "4.45.1"
16
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff