Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
RichardErkhov
/
trl-lib_-_Qwen2-0.5B-DPO-8bits
like
0
Safetensors
qwen2
8-bit precision
bitsandbytes
arxiv:
2305.18290
Model card
Files
Files and versions
Community
5ae140b
trl-lib_-_Qwen2-0.5B-DPO-8bits
/
tokenizer.json
RichardErkhov
uploaded model
eb59d89
verified
8 days ago
raw
Copy download link
history
Safe
7.03 MB
File too large to display, you can
check the raw version
instead.