Downloads · 30 days
57
3% of all-time downloads
RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Instruct-ORPO-v0.1-gguf
OwenArli_-_ArliAI-Llama-3-8B-Instruct-ORPO-v0.1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
57
3% of all-time downloads
All-time downloads
2.2K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
ArliAI-Llama-3-8B-Instruct-ORPO-v0.1 - GGUF
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:

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: