INC4AI commited on
Commit
18b3d41
·
verified ·
1 Parent(s): 958fe6a

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -0
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model:
4
+ - unsloth/DeepSeek-R1-BF16
5
+ ---
6
+ ## Model Details
7
+
8
+ This model card is for mxfp4 quantization of [unsloth/DeepSeek-R1-BF16](https://huggingface.co/unsloth/DeepSeek-R1-BF16) based on [intel/auto-round](https://github.com/intel/auto-round) saved in llm_compressor format.
9
+ Please follow the license of the original model.
10
+
11
+ ## How to Use
12
+
13
+ The step-by-step README of quantization and evaluation can be found in [Intel Neural Compressor Examples](https://github.com/intel/neural-compressor/blob/master/examples/pytorch/nlp/huggingface_models/language-modeling/quantization/auto_round/deepseek/README.md).
14
+
15
+ ## Evaluate
16
+
17
+ ```
18
+ # auto-round 0.14.2
19
+ # vllm 0.26.1rc1.dev451+gb1e12d142
20
+
21
+ export CUDA_VISIBLE_DEVICES=4,5,6,7
22
+ export VLLM_QDQ=1
23
+ python vllm/examples/basic/offline_inference/generate.py \
24
+ --model /software/data/jenkins/saved_models/DeepSeek-R1_mxfp4_LLMC/DeepSeek-R1-BF16-mxfp-w4g32/ \
25
+ --max-model-len 2048 \
26
+ -tp 4 \
27
+ --enforce-eager \
28
+ --gpu-memory-utilization 0.9
29
+ ```
30
+
31
+ ## Ethical Considerations and Limitations
32
+
33
+ The model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
34
+ Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
35
+
36
+ Therefore, before deploying any applications of the model, developers should perform safety testing.
37
+
38
+ ## Caveats and Recommendations
39
+
40
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
41
+
42
+ Here are a couple of useful links to learn more about Intel's AI software:
43
+
44
+ - [Intel Neural Compressor](https://github.com/intel/neural-compressor)
45
+ - [AutoRound](https://github.com/intel/auto-round)
46
+
47
+ ## Disclaimer
48
+
49
+ The license on this model does not constitute legal advice.
50
+ We are not responsible for the actions of third parties who use this model.
51
+ Please consult an attorney before using this model for commercial purposes.