Wenzhi Peng

pengwenzhi

·

pengwenzhi

AI & ML interests

None yet

Recent Activity

new activity about 15 hours ago

LiquidAI/LFM3-1.7B:vllm version for deploy?

new activity 2 days ago

XHToken/Spark-X2.6-4B:Spark-X2.6-4B and for the detailed answer on τ³-Banking in discussion #4. It made that number reproducible.

liked a model 2 days ago

LiquidAI/LFM3-1.7B

View all activity

Organizations

New activity in LiquidAI/LFM3-1.7B about 15 hours ago

vllm version for deploy?

#4 opened 1 day ago by

New activity in XHToken/Spark-X2.6-4B 2 days ago

Spark-X2.6-4B and for the detailed answer on τ³-Banking in discussion #4. It made that number reproducible.

#21 opened 2 days ago by

New activity in XHToken/Spark-X2.6-4B 6 days ago

关于Tau3分数的疑问

#4 opened 7 days ago by

New activity in unsloth/Qwen3.8-27B-GGUF 17 days ago

Which GGUF quantization would you recommend for an RTX 5080 (16GB VRAM)?

#131 opened about 1 month ago by

New activity in Gensyn/open-1b-sft about 1 month ago

Question about parameter count 1B

#1 opened about 1 month ago by

New activity in zgcagi/ZGCM-1-7B about 1 month ago

The model you test is out time! you should test spark-x2.5-4B or minicpm5-2B

#1 opened about 1 month ago by

New activity in ibm-granite/granite-4.2-3b about 2 months ago

Clarification on enabling and evaluating 512K context

#3 opened about 2 months ago by

New activity in openbmb/MiniCPM5-2B about 2 months ago

## Question about LongBench v2 evaluation with the 128K context limit

#7 opened about 2 months ago by

New activity in XHToken/Spark-X2.5-1.7B about 2 months ago

Spark-X2.5 Speed Benchmark

#9 opened about 2 months ago by

New activity in XHToken/Spark-X2.5-4B about 2 months ago

Spark-X2.5 Speed Benchmark

#7 opened about 2 months ago by

New activity in openbmb/MiniCPM5-1B 2 months ago

I reproduced the test-set results using the optimal hyperparameters, but the scores are lower than official report, is my parameters wrong?

#27 opened 2 months ago by

I reproduced the test-set results using the optimal hyperparameters, but the scores are lower than official report, is my parameters wrong?

#27 opened 2 months ago by