base_model, language, tags, license, datasets, pipeline_tag, license_name, license_link, model_creator, quantized_by

base_model	language	tags	license	datasets	pipeline_tag	license_name	license_link	model_creator	quantized_by
unsloth/Meta-Llama-3.1-8B-bnb-4bit	en	text-generation-inference transformers unsloth llama trl sft dpo	llama3.1	reciperesearch/dolphin-sft-v0.1-preference	text-generation	llama3	LICENSE	EpistemeAI	EpistemeAI

gguf:

• q4_k_m
• 16-bit

This model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license.

Fine-tune using ORPO

Training Details

Training Data

• dataset: reciperesearch/dolphin-sft-v0.1-preference

Training Procedure

ORPO techniques

Training Hyperparameters

• Training regime: {{ training_regime | default("[More Information Needed]", true)}}

TrainOutput(global_step=30, training_loss=4.25380277633667, metrics={'train_runtime': 679.3467, 'train_samples_per_second': 0.353, 'train_steps_per_second': 0.044, 'total_flos': 0.0, 'train_loss': 4.25380277633667, 'epoch': 0.015})