Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
SongTonyLi
/
gemma-2b-it-SFT-D1_chosen-then-DPO-D2a-distilabel-math-preference
like
0
Text Generation
Transformers
Safetensors
gemma
trl
dpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
1910.09700
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
gemma-2b-it-SFT-D1_chosen-then-DPO-D2a-distilabel-math-preference
1 contributor
History:
3 commits
SongTonyLi
Upload tokenizer
60170ff
verified
2 months ago
.gitattributes
1.57 kB
Upload tokenizer
2 months ago
README.md
5.18 kB
Upload GemmaForCausalLM
2 months ago
config.json
751 Bytes
Upload GemmaForCausalLM
2 months ago
generation_config.json
132 Bytes
Upload GemmaForCausalLM
2 months ago
model-00001-of-00002.safetensors
1.05 GB
LFS
Upload GemmaForCausalLM
2 months ago
model-00002-of-00002.safetensors
3.96 GB
LFS
Upload GemmaForCausalLM
2 months ago
model.safetensors.index.json
13.5 kB
Upload GemmaForCausalLM
2 months ago
special_tokens_map.json
636 Bytes
Upload tokenizer
2 months ago
tokenizer.json
17.5 MB
LFS
Upload tokenizer
2 months ago
tokenizer.model
4.24 MB
LFS
Upload tokenizer
2 months ago
tokenizer_config.json
40.5 kB
Upload tokenizer
2 months ago
