Update README.md

README.md

@@ -6,5 +6,86 @@ base_model:
 - moonshotai/Kimi-K2-Thinking
 ---
 
-- ## Disclaimer
-<span style="color:red; font-size:20px">Model under internal development and testing.</span>
+# Model Overview
+
+- **Model Architecture:** Kimi-K2-Thinking
+  - **Input:** Text
+  - **Output:** Text
+- **Supported Hardware Microarchitecture:** AMD MI300/MI355
+- **ROCm**: 7.0
+- **PyTorch**: 2.8.0
+- **Transformers**: 4.53.0
+- **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) (V0.10)
+  - **Weight quantization:** INT4 Per-Channel & FP8E4M3, Static
+  - **Activation quantization:** FP8E4M3, Dynamic
+
+This model was built with moonshotai Kimi-K2-Thinking model by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for INT4-FP8 quantization.
+
+# Model Quantization
+
+The model was quantized from [moonshotai/Kimi-K2-Thinking](https://huggingface.co/moonshotai/Kimi-K2-Thinking) using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). Both weights and activations were quantized to MXFP4 format. 
+
+# Deployment
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backends.
+
+## Evaluation
+
+The model was evaluated on GSM8K benchmarks using the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) framework.
+
+### Accuracy
+
+<table>
+  <tr>
+   <td><strong>Benchmark</strong>
+   </td>
+   <td><strong>Kimi-K2-Thinking </strong>
+   </td>
+   <td><strong>Kimi-K2-Thinking-W4A8(this model)</strong>
+   </td>
+   <td><strong>Recovery</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>GSM8K 
+   </td>
+   <td>93.93
+   </td>
+   <td>93.4
+   </td>
+   <td>99.4%
+   </td>
+  </tr>
+</table>
+
+
+### Reproduction
+
+The results of GSM8K were obtained using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) and latest vLLM. 
+
+Launch vLLM
+```
+MODEL_DIR=/data/amd/Kimi-K2-Thinking-W4A8
+VLLM_ATTENTION_BACKEND="TRITON_MLA" VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 vllm serve $MODEL_DIR \
+    --port 8001 \
+    --trust-remote-code \
+    --gpu-memory-utilization 0.9 \
+    --tensor-parallel-size 8 \
+    --load-format "fastsafetensors"
+```
+
+GSM8K evaluation
+```
+MODEL_ARGS="model=/data/amd/Kimi-K2-Thinking-W4A8,base_url=http://localhost:8001/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=38768,temperature=0.6,top_p=0.95,add_bos_token=True,seed=$SEED,trust_remote_code=True"
+lm_eval \
+    --model local-completions \
+    --model_args $MODEL_ARGS \
+    --tasks gsm8k \
+    --num_fewshot 8 \
+    --batch_size auto
+```
+
+# License
+Modifications Copyright(c) 2025 Advanced Micro Devices, Inc. All rights reserved.