ArliAI-Llama-3
Collection
Quantizations of ArliAI-Llama-3 models
•
15 items
•
Updated
•
1
This is quantized version of OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3 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
In terms of reasoning and intelligence, this model is probably a bit worse than the OG model because of the decensoring. However, this model is better at long back and forth chats and will refuse less.
OpenLLM Benchmark:
Training:
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-Cumulus-v0.3