Edit model card

Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct

ORPO fine tuning method using the following datasets:

Despite the toxic datasets to reduce refusals, this model is still relatively safe but refuses less than the original Meta model.

As of now ORPO fine tuning seems to improve some metrics while reducing other metrics by a lot:

OpenLLM Leaderboard

Instruct format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Quants:

Downloads last month
368
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for OwenArli/ArliAI-Llama-3-8B-Instruct-ORPO-v0.1

Quantizations
4 models

Spaces using OwenArli/ArliAI-Llama-3-8B-Instruct-ORPO-v0.1 5