INCModel1 commited on
Commit
89c7781
·
verified ·
1 Parent(s): 067fd10

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model:
4
+ - unsloth/DeepSeek-R1-BF16
5
+ ---
6
+ ## Model Details
7
+
8
+ This model card is for nvfp4 quantization of [unsloth/DeepSeek-R1-BF16](https://huggingface.co/unsloth/DeepSeek-R1-BF16) based on [intel/auto-round](https://github.com/intel/auto-round).
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 Results
16
+
17
+ | Task | backend | BF16 | NVFP4 |
18
+ |:-----------:|:-------:|:----------:|:----------:|
19
+ | hellaswag | vllm | 0.6903 | 0.6953 |
20
+ | piqa | vllm | 0.8319 | 0.8303 |
21
+ | mmlu | vllm | 0.8489 | 0.8495 |
22
+ | gsm8k | vllm | 0.9568 | 0.9606 |
23
+ | **average** | vllm | **0.8320** | **0.8339** |
24
+
25
+ ## Ethical Considerations and Limitations
26
+
27
+ The model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
28
+ 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.
29
+
30
+ Therefore, before deploying any applications of the model, developers should perform safety testing.
31
+
32
+ ## Caveats and Recommendations
33
+
34
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
35
+
36
+ Here are a couple of useful links to learn more about Intel's AI software:
37
+
38
+ - [Intel Neural Compressor](https://github.com/intel/neural-compressor)
39
+ - [AutoRound](https://github.com/intel/auto-round)
40
+
41
+ ## Disclaimer
42
+
43
+ The license on this model does not constitute legal advice.
44
+ We are not responsible for the actions of third parties who use this model.
45
+ Please consult an attorney before using this model for commercial purposes.