Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
mlabonne
/
OrpoLlama-3-8B
like
53
Text Generation
Transformers
Safetensors
mlabonne/orpo-dpo-mix-40k
English
llama
orpo
llama 3
rlhf
sft
conversational
text-generation-inference
Inference Endpoints
License:
other
Model card
Files
Files and versions
Community
6
Train
Deploy
Use this model
7f200e4
OrpoLlama-3-8B
/
generation_config.json
mlabonne
Upload LlamaForCausalLM
180ab05
verified
7 months ago
raw
Copy download link
history
blame
Safe
147 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
128256
,
"eos_token_id"
:
128257
,
"pad_token_id"
:
128257
,
"transformers_version"
:
"4.40.0"
}