Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
mayacinka
/
OkapiLlama-3-dpo
like
0
Text Generation
Transformers
Safetensors
mlabonne/orpo-dpo-mix-40k
English
llama
text-generation-inference
unsloth
trl
dpo
conversational
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
853a365
OkapiLlama-3-dpo
/
generation_config.json
mayacinka
Trained with Unsloth
853a365
verified
7 months ago
raw
Copy download link
history
blame
Safe
121 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
128000
,
"eos_token_id"
:
128001
,
"transformers_version"
:
"4.38.2"
}