Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
valerielucro
/
mistral_gsm8k_preference_dataset_v2_beta_6
like
0
Transformers
Safetensors
Inference Endpoints
arxiv:
1910.09700
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
mistral_gsm8k_preference_dataset_v2_beta_6
1 contributor
History:
3 commits
valerielucro
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
bf3aa78
verified
5 months ago
.gitattributes
1.52 kB
initial commit
5 months ago
README.md
5.18 kB
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago
adapter_config.json
753 Bytes
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago
adapter_model.safetensors
671 MB
LFS
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago
special_tokens_map.json
437 Bytes
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago
tokenizer.json
1.8 MB
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago
tokenizer.model
493 kB
LFS
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago
tokenizer_config.json
1.47 kB
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.6
5 months ago