Update README.md

README.md

@@ -32,8 +32,9 @@ base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
 - **License(s):** [llama3.1](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE)
 - **Model Developers:** Neural Magic
 
-Quantized version of [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct).
-It achieves an average score of 84.16 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 84.40.
+This model is a quantized version of [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct).
+It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model, including multiple-choice, math reasoning, and open-ended text generation.
+Meta-Llama-3.1-70B-Instruct-FP8-dynamic achieves 101.6% recovery for the Arena-Hard evaluation, 99.7% for OpenLLM v1 (using Meta's prompting when available), 100.0% for OpenLLM v2, 100.4% for HumanEval pass@1, and 100.3% for HumanEval+ pass@1.
 
 ### Model Optimizations
 
@@ -138,50 +139,73 @@ oneshot(
 
 ## Evaluation
 
-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, GSM-8K, MMLU, and MMLU-cot 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).
+This model was evaluated on the well-known Arena-Hard, OpenLLM v1, OpenLLM v2, HumanEval, and HumanEval+ benchmarks.
+In all cases, model outputs were generated with the [vLLM](https://docs.vllm.ai/en/stable/) engine.
+
+Arena-Hard evaluations were conducted using the [Arena-Hard-Auto](https://github.com/lmarena/arena-hard-auto) repository.
+The model generated a single answer for each prompt form Arena-Hard, and each answer was judged twice by GPT-4.
+We report below the scores obtained in each judgement and the average.
+
+OpenLLM v1 and v2 evaluations were conducted using Neural Magic's fork of [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness/tree/llama_3.1_instruct) (branch llama_3.1_instruct).
+This version of the lm-evaluation-harness includes versions of MMLU, 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-3.1-70B-Instruct-evals) and a few fixes to OpenLLM v2 tasks.
+
+HumanEval and HumanEval+ evaluations were conducted using Neural Magic's fork of the [EvalPlus](https://github.com/neuralmagic/evalplus) repository.
+
+Detailed model outputs are available as HuggingFace datasets for [Arena-Hard](https://huggingface.co/datasets/neuralmagic/quantized-llama-3.1-arena-hard-evals), [OpenLLM v2](https://huggingface.co/datasets/neuralmagic/quantized-llama-3.1-leaderboard-v2-evals), and [HumanEval](https://huggingface.co/datasets/neuralmagic/quantized-llama-3.1-humaneval-evals).
 
 ### Accuracy
 
-#### Open LLM Leaderboard evaluation scores
 <table>
   <tr>
    <td><strong>Benchmark</strong>
    </td>
    <td><strong>Meta-Llama-3.1-70B-Instruct </strong>
    </td>
-   <td><strong>Meta-Llama-3.1-70B-Instruct-FP8(this model)</strong>
+   <td><strong>Meta-Llama-3.1-70B-Instruct-FP8-dynamic (this model)</strong>
    </td>
    <td><strong>Recovery</strong>
    </td>
   </tr>
+  <tr>
+   <td><strong>Arena Hard</strong>
+   </td>
+   <td>57.0 (55.8 / 58.2)
+   </td>
+   <td>57.9 (58.1 / 57.7)
+   </td>
+   <td>101.6%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>OpenLLM v1</strong>
+   </td>
+  </tr>
   <tr>
    <td>MMLU (5-shot)
    </td>
-   <td>83.83
+   <td>83.8
    </td>
-   <td>83.75
+   <td>83.8
    </td>
-   <td>99.90%
+   <td>99.9%
    </td>
   </tr>
   <tr>
    <td>MMLU-cot (0-shot)
    </td>
-   <td>86.01
+   <td>86.0
    </td>
-   <td>85.48
+   <td>85.5
    </td>
-   <td>99.38%
+   <td>99.4%
    </td>
   </tr>
   <tr>
    <td>ARC Challenge (0-shot)
    </td>
-   <td>93.26
+   <td>93.3
    </td>
-   <td>93.52
+   <td>93.5
    </td>
    <td>100.2%
    </td>
@@ -189,51 +213,149 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge, GS
   <tr>
    <td>GSM-8K-cot (8-shot, strict-match)
    </td>
-   <td>94.92
+   <td>94.9
    </td>
-   <td>94.54
+   <td>94.5
    </td>
-   <td>99.60%
+   <td>99.6%
    </td>
   </tr>
   <tr>
    <td>Hellaswag (10-shot)
    </td>
-   <td>86.75
+   <td>86.8
    </td>
-   <td>86.63
+   <td>86.6
    </td>
-   <td>99.86%
+   <td>99.9%
    </td>
   </tr>
   <tr>
    <td>Winogrande (5-shot)
    </td>
-   <td>85.32
+   <td>85.3
    </td>
-   <td>84.61
+   <td>84.6
    </td>
-   <td>99.17%
+   <td>99.2%
    </td>
   </tr>
   <tr>
    <td>TruthfulQA (0-shot, mc2)
    </td>
-   <td>60.68
+   <td>60.7
    </td>
-   <td>60.60
+   <td>60.6
    </td>
-   <td>99.87%
+   <td>99.9%
    </td>
   </tr>
   <tr>
    <td><strong>Average</strong>
    </td>
-   <td><strong>84.40</strong>
+   <td><strong>84.4</strong>
+   </td>
+   <td><strong>84.2</strong>
    </td>
-   <td><strong>84.16</strong>
+   <td><strong>99.7%</strong>
    </td>
-   <td><strong>99.72%</strong>
+  </tr>
+  <tr>
+   <td><strong>OpenLLM v2</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>MMLU-Pro (5-shot)
+   </td>
+   <td>48.1
+   </td>
+   <td>47.7
+   </td>
+   <td>99.1%
+   </td>
+  </tr>
+  <tr>
+   <td>IFEval (0-shot)
+   </td>
+   <td>86.4
+   </td>
+   <td>87.6
+   </td>
+   <td>101.3%
+   </td>
+  </tr>
+  <tr>
+   <td>BBH (3-shot)
+   </td>
+   <td>55.8
+   </td>
+   <td>54.9
+   </td>
+   <td>98.4%
+   </td>
+  </tr>
+  <tr>
+   <td>Math-|v|-5 (4-shot)
+   </td>
+   <td>26.1
+   </td>
+   <td>28.0
+   </td>
+   <td>107.5%
+   </td>
+  </tr>
+  <tr>
+   <td>GPQA (0-shot)
+   </td>
+   <td>15.4
+   </td>
+   <td>14.6
+   </td>
+   <td>94.7%
+   </td>
+  </tr>
+  <tr>
+   <td>MuSR (0-shot)
+   </td>
+   <td>18.2
+   </td>
+   <td>17.2
+   </td>
+   <td>94.5%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>41.7</strong>
+   </td>
+   <td><strong>41.7</strong>
+   </td>
+   <td><strong>100.0%</strong>
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Coding</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>HumanEval pass@1
+   </td>
+   <td>79.7
+   </td>
+   <td>80.0
+   </td>
+   <td>100.4%
+   </td>
+  </tr>
+  <tr>
+   <td>HumanEval+ pass@1
+   </td>
+   <td>74.8
+   </td>
+   <td>75.0
+   </td>
+   <td>100.3%
    </td>
   </tr>
 </table>
@@ -314,4 +436,39 @@ lm_eval \
   --tasks truthfulqa \
   --num_fewshot 0 \
   --batch_size auto
+```
+
+#### OpenLLM v2
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True \
+  --apply_chat_template \
+  --fewshot_as_multiturn \
+  --tasks leaderboard \
+  --batch_size auto
+```
+
+#### HumanEval and HumanEval+
+##### Generation
+```
+python3 codegen/generate.py \
+  --model neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic \
+  --bs 16 \
+  --temperature 0.2 \
+  --n_samples 50 \
+  --root "." \
+  --dataset humaneval \
+  --tp 2
+```
+##### Sanitization
+```
+python3 evalplus/sanitize.py \
+  humaneval/neuralmagic--Meta-Llama-3.1-70B-Instruct-FP8-dynamic_vllm_temp_0.2
+```
+##### Evaluation
+```
+evalplus.evaluate \
+  --dataset humaneval \
+  --samples humaneval/neuralmagic--Meta-Llama-3.1-70B-Instruct-FP8-dynamic_vllm_temp_0.2-sanitized
 ```