Update README.md

README.md

@@ -77,35 +77,26 @@ The model was evaluated on gsm8k benchmarks using the [vllm](https://github.com/
 
 ### Reproduction
 
-The GSM8K results were obtained using the vLLM framework, based on the Docker image `rocm/vllm:rocm7.0.0_vllm_0.11.2_20251210`, and vLLM is installed inside the container with fixes applied for model support.
+The GSM8K results were obtained using the lm-eval framework, based on the Docker image `rocm/vllm-dev:nightly`.
 
-#### Preparation in container
-```
-# Reinstall vLLM
-pip uninstall vllm -y
-git clone https://github.com/vllm-project/vllm.git
-cd vllm
-git checkout v0.13.0
-pip install -r requirements/rocm.txt
-python setup.py develop
-cd ..
+#### Evaluating model in a new terminal
 ```
+export VLLM_ROCM_USE_AITER=1
 
-#### Launching server
-```
-VLLM_ROCM_USE_AITER=1 \
-VLLM_DISABLE_COMPILE_CACHE=1 \
-vllm serve "$MODEL" \
-    --tensor-parallel-size 4 \
-    --trust-remote-code \
-    --max-model-len 32768 \
-    --port 8899  
-```
+export model_dir_fp4=MiniMaxAI/MiniMax-M2.5-mxfp4/
+log_file=minimax25-lm_eval_gsm8k_mxfp4.txt
 
+lm_eval --model vllm --model_args pretrained=$model_dir_fp4,enforce_eager=True,trust_remote_code=True,max_model_len=16384 \
+        --gen_kwargs temperature=1.0,top_p=0.95,top_k=40 \
+        --tasks gsm8k  --num_fewshot 8 2>&1 | tee $log_file
 
-#### Evaluating model in a new terminal
-```
-python vllm/tests/evals/gsm8k/gsm8k_eval.py --host http://127.0.0.1 --port 8899 --num-questions 1000 --save-results logs
+
+export model_dir=MiniMaxAI/MiniMax-M2.5/
+log_file=minimax25-lm_eval_gsm8k.txt
+
+lm_eval --model vllm --model_args pretrained=$model_dir,enforce_eager=True,tensor_parallel_size=8,trust_remote_code=True,max_model_len=16384 \
+        --gen_kwargs temperature=0.8,top_p=0.95,top_k=40 \
+        --tasks gsm8k  --num_fewshot 8 2>&1 | tee $log_file
 ```