Update README.md

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model:
 - Qwen/Qwen3-8B
 ---
+
+## Introduce
 We adapted the official speculative sampling training method, Eagle3, for training on Qwen3-30B-A3B
 
 After implementing Eagle3, the inference performance of Qwen3-8B using the SGLang framework on 8*H200 GPU improved from 183 tokens/s to 325 tokens/s.
@@ -19,6 +21,7 @@ To use Eagle3 with SGLang, first replace the qwen3_moe.py file in SGLang’s dir
 | qwen3-30b_moe   | 8*h200   | 183   |
 | qwen3-30b_moe-eagle3  | 8*h200  | 325  |
 
+## How to use
 
 The launch command for using Eagle3 with SGLang is:
 
@@ -27,4 +30,16 @@ The launch command for using Eagle3 with SGLang is:
 python3 -m sglang.launch_server --model Qwen/Qwen3-30B-A3B --speculative-algorithm EAGLE3 --speculative-draft-model-path Tengyunw/qwen3_30b_moe_eagle3 --speculative-num-steps 6 --speculative-eagle-topk 10 --speculative-num-draft-tokens 32 --mem-fraction 0.9 --cuda-graph-max-bs 2 --dtype bfloat16
 
 ```
-Our test data is located in the eagle_data.jsonl file under this directory.
+
+## how to train
+
+Training Dataset:
+ultrachat_200k.
+Only the prompts from these datasets were utilized for data synthesis, excluding the original responses from Qwen3. This synthesized data is used to train the Eagle modules. 
+
+dataset nums: 600K samples,1B tokens
+
+Evaluation Dataset:
+ShareGPT,GSM8K,HUAMEVAL,MT-BENCH,APLCA
+
+Our Sharegpt test data is located in the eagle_data.jsonl file under this directory.