Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
vessl
/
llama-3-8b-bnb-4bit-dpo-qlora
like
0
Follow
VESSL AI
16
Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
dpo
Inference Endpoints
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
llama-3-8b-bnb-4bit-dpo-qlora
1 contributor
History:
4 commits
lucasnam
Trained with Unsloth
186049e
verified
10 months ago
.gitattributes
Safe
1.52 kB
initial commit
10 months ago
README.md
Safe
578 Bytes
Trained with Unsloth
10 months ago
config.json
Safe
1.14 kB
Trained with Unsloth
10 months ago
generation_config.json
Safe
172 Bytes
Trained with Unsloth
10 months ago
model-00001-of-00002.safetensors
Safe
5 GB
LFS
Trained with Unsloth
10 months ago
model-00002-of-00002.safetensors
Safe
2.81 GB
LFS
Trained with Unsloth
10 months ago
model.safetensors.index.json
Safe
132 kB
Trained with Unsloth
10 months ago
special_tokens_map.json
Safe
464 Bytes
Trained with Unsloth
10 months ago
tokenizer.json
Safe
9.09 MB
Trained with Unsloth
10 months ago
tokenizer_config.json
Safe
50.6 kB
Trained with Unsloth
10 months ago
