Hugging Face's logo

pytorch
/
Qwen3-32B-float8dq

Text Generation
Transformers
PyTorch
multilingual
qwen3
torchao
code
math
chat
conversational
text-generation-inference
Model card Files Community
jerryzh168 commited on
Commit
a3302a3
·
verified ·
1 Parent(s): 23ccbd2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -10
README.md CHANGED
@@ -129,19 +129,15 @@ We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-h
129
 
130
  | Benchmark | | |
131
  |----------------------------------|----------------|---------------------------|
132
- | | Qwen3-32B | Qwen3-32B-float8dq |
133
  | **General** | | |
134
- | mmlu | WIP | WIP |
135
- | mmlu_pro | WIP | WIP |
136
- | bbh | WIP | WIP |
137
  | **Multilingual** | | |
138
- | mgsm_en_cot_en | WIP | WIP |
139
- | m_mmlu (avg) | WIP | WIP |
140
  | **Math** | | |
141
- | gpqa_main_zeroshot | WIP | WIP |
142
- | gsm8k | WIP | WIP |
143
- | leaderboard_math_hard (v3) | WIP | WIP |
144
- | **Overall** | WIP | WIP |
145
 
146
  <details>
147
  <summary> Reproduce Model Quality Results </summary>
 
129
 
130
  | Benchmark | | |
131
  |----------------------------------|----------------|---------------------------|
132
+ | | Qwen3-32B | Qwen3-32B-float8dq |
133
  | **General** | | |
134
+ | mmlu | 80.71 | 80.67 |
135
+ | bbh | 37.49 | 38.01 |
 
136
  | **Multilingual** | | |
137
+ | mgsm_en_cot_en | 64.40 | WIP |
 
138
  | **Math** | | |
139
+ | gpqa_main_zeroshot | 41.96 | 42.63 |
140
+ | **Overall** | 56.14 | WIP |
 
 
141
 
142
  <details>
143
  <summary> Reproduce Model Quality Results </summary>