Hugging Face's logo

mlabonne
/
TwinLlama-3.1-8B-DPO

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
dpo
Inference Endpoints
Model card Files Community

Uploaded model

  • Developed by: mlabonne
  • License: apache-2.0
  • Finetuned from model : mlabonne/TwinLlama-3.1-8B

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
189
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
Text Generation
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for mlabonne/TwinLlama-3.1-8B-DPO

Base model

meta-llama/Llama-3.1-8B
Finetuned
mlabonne/TwinLlama-3.1-8B
Finetuned
(1)
this model
Quantizations
3 models

Space using mlabonne/TwinLlama-3.1-8B-DPO 1