ArliAI-Llama-3
Collection
Quantizations of ArliAI-Llama-3 models • 15 items • Updated • 2
How to use from
vLLMUse Docker
docker model run hf.co/QuantFactory/ArliAI-Llama-3-8B-Argon-v1.0-GGUF:Quick Links
QuantFactory/ArliAI-Llama-3-8B-Argon-v1.0-GGUF
This is quantized version of OwenArli/ArliAI-Llama-3-8B-Argon-v1.0 created using llama.cpp
Model Description
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
Experimental model trying to make Llama 3 8B better in general overall. Pretty difficult to do.
Base model: https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
Training:
- 4096 sequence length
- Training duration is around 2 days on 2x3090Ti
- 1 epoch training with a massive dataset for minimized repetition sickness.
- LORA with 64-rank 128-alpha resulting in ~2% trainable weights.
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|>
- Downloads last month
- 158
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "QuantFactory/ArliAI-Llama-3-8B-Argon-v1.0-GGUF"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuantFactory/ArliAI-Llama-3-8B-Argon-v1.0-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'