README.md

---
license: llama3.1
base_model:
- meta-llama/Llama-3.1-405B-Instruct
---

# Model Overview

- **Model Architecture:** Llama-3.1
  - **Input:** Text
  - **Output:** Text
- **Supported Hardware Microarchitecture:** AMD MI350/MI355
- **ROCm**: 7.0
- **Preferred Operating System(s):** Linux
- **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (V0.9)
  - **Weight quantization:** OCP MXFP4, Static
  - **Activation quantization:** OCP MXFP4, Dynamic
  - **KV cache quantization:** OCP FP8, Static 
- **Calibration Dataset:** [Pile](https://huggingface.co/datasets/mit-han-lab/pile-val-backup)

This model was built with Meta Llama by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for MXFP4 quantization.

# Model Quantization

The model was quantized from [meta-llama/Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct) using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). Weights and activations were quantized to MXFP4, and KV caches were quantized to FP8. The AutoSmoothQuant algorithm was applied to enhance accuracy during quantization.

**Quantization scripts:**
```
cd Quark/examples/torch/language_modeling/llm_ptq/
python3 quantize_quark.py --model_dir "meta-llama/Llama-3.1-405B-Instruct" \
                          --model_attn_implementation "sdpa" \
                          --quant_scheme w_mxfp4_a_mxfp4 \
                          --group_size 32 \
                          --kv_cache_dtype fp8 \
                          --quant_algo autosmoothquant \
                          --min_kv_scale 1.0 \
                          --model_export hf_format \
                          --output_dir amd/Llama-3.1-405B-Instruct-MXFP4 \
                          --multi_gpu
```

# Deployment
### Use with vLLM

This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend.

## Evaluation

The model was evaluated on MMLU and GSM8K_COT.
Evaluation was conducted using the framework [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) and the vLLM engine.

### Accuracy

<table>
  <tr>
   <td><strong>Benchmark</strong>
   </td>
   <td><strong>Llama-3.1-405B-Instruct </strong>
   </td>
   <td><strong>Llama-3.1-405B-Instruct-MXFP4(this model)</strong>
   </td>
   <td><strong>Recovery</strong>
   </td>
  </tr>
  <tr>
   <td>MMLU (5-shot)
   </td>
   <td>87.63
   </td>
   <td>86.62
   </td>
   <td>98.85%
   </td>
  </tr>
  <tr>
   <td>GSM8K_COT (8-shot, strict-match)
   </td>
   <td>96.51
   </td>
   <td>96.06
   </td>
   <td>99.53%
   </td>
  </tr>
</table>


### Reproduction

The results were obtained using the following commands:

#### MMLU
```
lm_eval \
    --model vllm \
    --model_args pretrained="amd/Llama-3.1-405B-Instruct-MXFP4-Preview",gpu_memory_utilization=0.85,tensor_parallel_size=8,kv_cache_dtype='fp8' \
    --tasks mmlu_llama \
    --fewshot_as_multiturn \
    --apply_chat_template \
    --num_fewshot 5 \
    --batch_size auto
```

#### GSM8K_COT
```
lm_eval \
    --model vllm \
    --model_args pretrained="amd/Llama-3.1-405B-Instruct-MXFP4-Preview",gpu_memory_utilization=0.85,tensor_parallel_size=8,kv_cache_dtype='fp8' \
    --tasks gsm8k_llama \
    --fewshot_as_multiturn \
    --apply_chat_template \
    --num_fewshot 8 \
    --batch_size auto
```

# License

Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.