metadata
license: llama3.1
GGUF llama.cpp quantized version of:
- Original model: Meta-Llama-3.1-8B-Instruct
- Model creator: Meta
- License
Update(24/07/27): Latest fixes to use the full 128k context window are included in -ropefix versions. Requirement to run them and used version: b3472
Update: Use the -imatrix versions (they use imatrix and the bpe-llama tokenizer which should theoretically improve the output)
Recommended Prompt Format (Llama3)
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Provide some context and/or instructions to the model.<|eot_id|><|start_header_id|>user<|end_header_id|>
The user’s message goes here<|eot_id|><|start_header_id|>assistant<|end_header_id|>
AI message goes here<|eot_id|>
Quant Version: b3445