linzhao-amd commited on
Commit
6cf028a
·
verified ·
1 Parent(s): 11b5d19

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -103,13 +103,13 @@ The model was evaluated on AIME24, GPQA Diamond, and MATH-500 benchmarks using t
103
  The results were obtained using the following commands, with custom tasks and 10 rounds using different random seeds.
104
 
105
  ```
106
- MODEL_ARGS="model_name=amd/DeepSeek-R1-0528-MXFP4-ASQ,dtype=bfloat16,tensor_parallel_size=8,max_model_length=71536,max_num_batched_tokens=32768,gpu_memory_utilization=0.85,generation_parameters={max_new_tokens:65536,temperature:0.6,top_p:0.95,seed:$SEED}"
107
- OUTPUT_DIR="results/DeepSeek-R1-0528-MXFP4-ASQ-Seed"
108
  LOG="logs/deepseek_0528_maxfp4.log"
109
 
110
  lighteval vllm $MODEL_ARGS "custom|aime24_single|0|0,custom|math_500_single|0|0,custom|gpqa:diamond_single|0|0" \
111
  --use-chat-template \
112
- --output-dir "results/DeepSeek-R1-0528-MXFP4-ASQ-Seed/seed_$SEED" \
113
  2>&1 | tee -a "$LOG"
114
  ```
115
 
 
103
  The results were obtained using the following commands, with custom tasks and 10 rounds using different random seeds.
104
 
105
  ```
106
+ MODEL_ARGS="model_name=amd/DeepSeek-R1-0528-MXFP4-Preview,dtype=bfloat16,tensor_parallel_size=8,max_model_length=71536,max_num_batched_tokens=32768,gpu_memory_utilization=0.85,generation_parameters={max_new_tokens:65536,temperature:0.6,top_p:0.95,seed:$SEED}"
107
+ OUTPUT_DIR="results/DeepSeek-R1-0528-MXFP4-Preview-Seed"
108
  LOG="logs/deepseek_0528_maxfp4.log"
109
 
110
  lighteval vllm $MODEL_ARGS "custom|aime24_single|0|0,custom|math_500_single|0|0,custom|gpqa:diamond_single|0|0" \
111
  --use-chat-template \
112
+ --output-dir "$OUTPUT_DIR/seed_$SEED" \
113
  2>&1 | tee -a "$LOG"
114
  ```
115