ColinZ22 commited on
Commit
985ea5a
·
verified ·
1 Parent(s): 9e1792b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -58,7 +58,7 @@ The model was evaluated on GSM8K and GPQA-Diamond-CoT benchmarks.
58
  </td>
59
  <td><strong>zai-org/GLM-5.2</strong>
60
  </td>
61
- <td><strong>amd/GLM-5.2-MXFP4-AttnFP8 (this model)</strong>
62
  </td>
63
  <td><strong>Recovery</strong>
64
  </td>
@@ -96,7 +96,7 @@ export VLLM_ROCM_USE_AITER_FP4BMM=0
96
 
97
  lm_eval \
98
  --model vllm \
99
- --model_args "pretrained=amd/GLM-5.2-MXFP4-AttnFP8,tensor_parallel_size=4,dtype=auto,quantization=quark,gpu_memory_utilization=0.9,max_model_len=40960,trust_remote_code=True" \
100
  --tasks gsm8k gpqa_diamond_cot_zeroshot \
101
  --apply_chat_template \
102
  --gen_kwargs "max_gen_toks=32768,temperature=1.0,top_p=0.95,do_sample=True" \
 
58
  </td>
59
  <td><strong>zai-org/GLM-5.2</strong>
60
  </td>
61
+ <td><strong>amd/GLM-5.2-Quark-MXFP4-AttnFP8 (this model)</strong>
62
  </td>
63
  <td><strong>Recovery</strong>
64
  </td>
 
96
 
97
  lm_eval \
98
  --model vllm \
99
+ --model_args "pretrained=amd/GLM-5.2-Quark-MXFP4-AttnFP8,tensor_parallel_size=4,dtype=auto,quantization=quark,gpu_memory_utilization=0.9,max_model_len=40960,trust_remote_code=True" \
100
  --tasks gsm8k gpqa_diamond_cot_zeroshot \
101
  --apply_chat_template \
102
  --gen_kwargs "max_gen_toks=32768,temperature=1.0,top_p=0.95,do_sample=True" \