Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
davidhornshaw
/
Qwen2.5-3B-ORPO
like
0
Text Generation
Safetensors
mlabonne/orpo-dpo-mix-40k
English
qwen2
arxiv:
2106.09685
arxiv:
2005.14165
License:
qwen-research
Model card
Files
Files and versions
Community
main
Qwen2.5-3B-ORPO
1 contributor
History:
16 commits
davidhornshaw
Added more detail to training hyperparams
953bad0
verified
25 days ago
.gitattributes
Safe
1.52 kB
initial commit
26 days ago
README.md
Safe
9.15 kB
Added more detail to training hyperparams
25 days ago
config.json
Safe
747 Bytes
Upload Qwen2ForCausalLM
26 days ago
eval_results.png
Safe
25.1 kB
Upload eval_results.png
25 days ago
generation_config.json
Safe
122 Bytes
Upload Qwen2ForCausalLM
26 days ago
model-00001-of-00003.safetensors
Safe
4.98 GB
LFS
Upload Qwen2ForCausalLM
26 days ago
model-00002-of-00003.safetensors
Safe
4.93 GB
LFS
Upload Qwen2ForCausalLM
26 days ago
model-00003-of-00003.safetensors
Safe
2.43 GB
LFS
Upload Qwen2ForCausalLM
26 days ago
model.safetensors.index.json
Safe
35.6 kB
Upload Qwen2ForCausalLM
26 days ago