Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
aryan14072001
/
CNN-DPO-LoRA
like
0
Text Generation
PEFT
Safetensors
Transformers
dpo
lora
sft
trl
unsloth
conversational
arxiv:
1910.09700
Model card
Files
Files and versions
xet
Community
Use this model
main
CNN-DPO-LoRA
62.4 MB
1 contributor
History:
2 commits
aryan14072001
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
b414e1e
verified
9 days ago
.gitattributes
1.57 kB
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
README.md
5.27 kB
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
adapter_config.json
1.21 kB
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
adapter_model.safetensors
45.1 MB
xet
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
chat_template.jinja
3.83 kB
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
special_tokens_map.json
454 Bytes
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
tokenizer.json
17.2 MB
xet
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
tokenizer_config.json
50.6 kB
LoRA adapter: SFT (CNN style) + DPO (anti-hallucination)
9 days ago
