INC4AI commited on
Commit
7917465
·
verified ·
1 Parent(s): 15f73ed

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -9
README.md CHANGED
@@ -6,7 +6,7 @@ base_model:
6
  ## Model Details
7
 
8
  This model card is for mxfp4 quantization of [meta-llama/Llama-4-Scout-17B-16E-Instruct](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct) based on [intel/auto-round](https://github.com/intel/auto-round).
9
- The quantized model is not able to be published due to the license limitation. Please follow the INC example README to generate and evaluate the low precision model.
10
 
11
  ## How to Use
12
 
@@ -14,14 +14,16 @@ The step-by-step README of quantization and evaluation can be found in [Intel Ne
14
 
15
  ## Evaluate Results
16
 
17
- | Task | backend | BF16 | MXFP4 |
18
- |:---------:|:-------:|:--------:|:------:|
19
- | hellaswag | vllm | 0.6389 | 0.6349 |
20
- | piqa | vllm | 0.8156 | 0.8107 |
21
- | mmlu | vllm | 0.7997 | 0.7921 |
22
- | gsm8k | vllm | 0.9090 | 0.9121 |
23
- | chartqa | vllm | 0.8900 | 0.8884 |
24
- | mmmu_val | vllm | 0.5989 | 0.5844 |
 
 
25
 
26
  ## Ethical Considerations and Limitations
27
 
 
6
  ## Model Details
7
 
8
  This model card is for mxfp4 quantization of [meta-llama/Llama-4-Scout-17B-16E-Instruct](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct) based on [intel/auto-round](https://github.com/intel/auto-round).
9
+ The quantized model is not able to be published due to license limitation. Please follow the INC example README to generate and evaluate the low precision model.
10
 
11
  ## How to Use
12
 
 
14
 
15
  ## Evaluate Results
16
 
17
+ | Task | backend | BF16 | MXFP4 |
18
+ |:-----------------:|:-------:|:--------:|:------:|
19
+ | hellaswag | vllm | 0.6389 | 0.6349 |
20
+ | piqa | vllm | 0.8156 | 0.8107 |
21
+ | mmlu | vllm | 0.7997 | 0.7921 |
22
+ | gsm8k(strict) | vllm | 0.9090 | 0.9121 |
23
+ | chartqa(relaxed) | vllm | 0.8900 | 0.8884 |
24
+ | mmmu_val | vllm | 0.5989 | 0.5844 |
25
+ | average | vllm | 0.7754 | 0.7704 |
26
+
27
 
28
  ## Ethical Considerations and Limitations
29