CHU Tianxiang
keyfan
AI & ML interests
None yet
Organizations
None yet
keyfan's activity
[WIP] Fix float32 precision (multi-commit 6f4f3fee98ff848b483b84b692a4b03251126f470852d10f1205f6af709627e7)
#5 opened 8 months ago
by
keyfan
Fix typo in modeling_grok
#3 opened 8 months ago
by
keyfan
Is RoPE scaling correct?
2
#2 opened 8 months ago
by
Noeda
量化设备
3
#3 opened 8 months ago
by
tiantian7777
Is there a big performance difference between 2bit quantization and 4bit quantization conversations?
1
#2 opened 10 months ago
by
xldistance
Upload folder using huggingface_hub
#1 opened 11 months ago
by
keyfan
Upload folder using huggingface_hub
#1 opened 11 months ago
by
keyfan