Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen2.5-Coder-0.5B-QwQ-draft-exl2_4.65bpw – AI Model by async0x42 | AlphaNeural AI
You can deploy this model and start earning money today!
async0x42
/
Qwen2.5-Coder-0.5B-QwQ-draft-exl2_4.65bpw
like
0
transformers
qwen2
text-generation
conversational
PowerInfer/QWQ-LONGCOT-500K
Qwen/Qwen2.5-Coder-0.5B-Instruct
quantized
autotrain_compatible
endpoints_compatible
exl2
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen2.5-Coder-0.5B-QwQ-draft
A draft model trained for
Qwen/QwQ-32B-Preview
vocabulary size of 152064, same as QwQ-32B-Preview (can be used in VLLM directly without any hack)
trained from
Qwen/Qwen2.5-Coder-0.5B-Instruct
on
PowerInfer/QWQ-LONGCOT-500K
2 epochs
draft acceptance rate above 0.8
up to x2.5 token speed in math problems (33 toks/s vs. 85 toks/s)