ArliAI-Llama-3-8B-Cumulus-v0.3

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:

• Full 8192 sequence length.
• Training duration is around 2 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 64-alpha resulting in ~2% trainable weights.

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:

FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3

GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3-GGUF