Upload model Qwen2.5-7B-Instruct-v8-k65536-256-woft
Browse files- .gitattributes +1 -0
- README.md +12 -12
- config.json +2 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- 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
|
@@ -1,9 +1,9 @@
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
license_name: qwen
|
| 4 |
-
license_link: https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE
|
| 5 |
---
|
| 6 |
-
|
| 7 |
**Disclaimer**:
|
| 8 |
|
| 9 |
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)
|
|
@@ -20,14 +20,14 @@ The PPL test results are for reference only and were collected using GPTQ testin
|
|
| 20 |
|
| 21 |
```json
|
| 22 |
{
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
}
|
| 33 |
-
```
|
|
|
|
| 1 |
+
|
| 2 |
---
|
| 3 |
license: other
|
| 4 |
license_name: qwen
|
| 5 |
+
license_link: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE
|
| 6 |
---
|
|
|
|
| 7 |
**Disclaimer**:
|
| 8 |
|
| 9 |
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)
|
|
|
|
| 20 |
|
| 21 |
```json
|
| 22 |
{
|
| 23 |
+
"ctx_2048": {
|
| 24 |
+
"wikitext2": 7.946412086486816
|
| 25 |
+
},
|
| 26 |
+
"ctx_4096": {
|
| 27 |
+
"wikitext2": 7.310400009155273
|
| 28 |
+
},
|
| 29 |
+
"ctx_8192": {
|
| 30 |
+
"wikitext2": 6.938364028930664
|
| 31 |
+
}
|
| 32 |
}
|
| 33 |
+
```
|
config.json
CHANGED
|
@@ -4723,11 +4723,12 @@
|
|
| 4723 |
}
|
| 4724 |
},
|
| 4725 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 4726 |
"rope_theta": 1000000.0,
|
| 4727 |
"sliding_window": null,
|
| 4728 |
"tie_word_embeddings": false,
|
| 4729 |
"torch_dtype": "bfloat16",
|
| 4730 |
-
"transformers_version": "4.
|
| 4731 |
"use_cache": true,
|
| 4732 |
"use_sliding_window": false,
|
| 4733 |
"vocab_size": 152064
|
|
|
|
| 4723 |
}
|
| 4724 |
},
|
| 4725 |
"rms_norm_eps": 1e-06,
|
| 4726 |
+
"rope_scaling": null,
|
| 4727 |
"rope_theta": 1000000.0,
|
| 4728 |
"sliding_window": null,
|
| 4729 |
"tie_word_embeddings": false,
|
| 4730 |
"torch_dtype": "bfloat16",
|
| 4731 |
+
"transformers_version": "4.45.1",
|
| 4732 |
"use_cache": true,
|
| 4733 |
"use_sliding_window": false,
|
| 4734 |
"vocab_size": 152064
|
generation_config.json
CHANGED
|
@@ -11,5 +11,5 @@
|
|
| 11 |
"temperature": 0.7,
|
| 12 |
"top_k": 20,
|
| 13 |
"top_p": 0.8,
|
| 14 |
-
"transformers_version": "4.
|
| 15 |
}
|
|
|
|
| 11 |
"temperature": 0.7,
|
| 12 |
"top_k": 20,
|
| 13 |
"top_p": 0.8,
|
| 14 |
+
"transformers_version": "4.45.1"
|
| 15 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4840913528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:917247bc869864084d6eb0af3b8d5d8e9b3596367eed405bc7cbbce8971ea1f1
|
| 3 |
size 4840913528
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|