Update README.md

README.md

@@ -20,15 +20,15 @@ license: llama3.1
   - **Output:** Text
 - **Model Optimizations:**
   - **Weight quantization:** INT8
-- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct), this models is intended for assistant-like chat.
-- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
+- **Intended Use Cases:** Intended for commercial and research use multiple languages. Similarly to [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct), this models is intended for assistant-like chat.
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws).
 - **Release Date:** 7/23/2024
 - **Version:** 1.0
 - **License(s):** [Llama3](https://llama.meta.com/llama3/license/)
 - **Model Developers:** Neural Magic
 
 Quantized version of [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
-It achieves an average score of 69.48 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 69.33.
+It achieves scores within 1% of the scores of the unquantized model for MMLU, ARC-Challenge, GSM-8k, Hellaswag, Winogrande and TruthfulQA.
 
 ### Model Optimizations
 
@@ -123,14 +123,9 @@ model.save_pretrained("Meta-Llama-3.1-8B-Instruct-quantized.w8a16")
 
 ## Evaluation
 
-The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) leaderboard tasks (version 1) with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/383bbd54bc621086e05aa1b030d8d4d5635b25e6) (commit 383bbd54bc621086e05aa1b030d8d4d5635b25e6) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command:
-```
-lm_eval \
-  --model vllm \
-  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
-  --tasks openllm \
-  --batch_size auto
-```
+The model was evaluated on MMLU, ARC-Challenge, GSM-8K, Hellaswag, Winogrande and TruthfulQA.
+Evaluation was conducted using the Neural Magic fork of [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness/tree/llama_3.1_instruct) (branch llama_3.1_instruct) and the [vLLM](https://docs.vllm.ai/en/stable/) engine.
+This version of the lm-evaluation-harness includes versions of ARC-Challenge and GSM-8K that match the prompting style of [Meta-Llama-3.1-Instruct-evals](https://huggingface.co/datasets/meta-llama/Meta-Llama-3.1-8B-Instruct-evals).
 
 ### Accuracy
 
@@ -157,23 +152,23 @@ lm_eval \
    </td>
   </tr>
   <tr>
-   <td>ARC Challenge (25-shot)
+   <td>ARC Challenge (0-shot)
    </td>
-   <td>60.41
+   <td>83.19
    </td>
-   <td>61.09
+   <td>82.68
    </td>
-   <td>101.1%
+   <td>99.4%
    </td>
   </tr>
   <tr>
-   <td>GSM-8K (5-shot, strict-match)
+   <td>GSM-8K (CoT, 8-shot, strict-match)
    </td>
-   <td>75.66
+   <td>82.79
    </td>
-   <td>76.04
+   <td>82.64
    </td>
-   <td>100.5%
+   <td>99.8%
    </td>
   </tr>
   <tr>
@@ -216,4 +211,70 @@ lm_eval \
    <td><strong>100.2%</strong>
    </td>
   </tr>
-</table>
+</table>
+
+### Reproduction
+
+The results were obtained using the following commands:
+
+#### MMLU
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --tasks mmlu \
+  --num_fewshot 5 \
+  --batch_size auto
+```
+
+#### ARC-Challenge
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --tasks arc_challenge_llama_3.1_instruct \
+  --apply_chat_template \
+  --num_fewshot 0 \
+  --batch_size auto
+```
+
+#### GSM-8K
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --tasks gsm8k_cot_llama_3.1_instruct \
+  --apply_chat_template \
+  --num_fewshot 8 \
+  --batch_size auto
+```
+
+#### Hellaswag
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --tasks hellaswag \
+  --num_fewshot 10 \
+  --batch_size auto
+```
+
+#### Winogrande
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --tasks winogrande \
+  --num_fewshot 5 \
+  --batch_size auto
+```
+
+#### Hellaswag
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+  --tasks truthfulqa_mc \
+  --num_fewshot 0 \
+  --batch_size auto
+```