ArliAI-Llama-3
Collection
Quantizations of ArliAI-Llama-3 models
•
15 items
•
Updated
•
1
This is quantized version of OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.2 created using llama.cpp
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
Realized a tokenization mistake with the previous DPO model. So this is now a new version testing out DPO training on the following dataset:
The open LLM results are really BAD lol. Something with this dataset is disagreeing with llama 3?
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|>
Base model
OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.2