|
--- |
|
license: mit |
|
tags: |
|
- gguf |
|
--- |
|
GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of: |
|
- Original model: [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) |
|
- Model creator: [Microsoft](https://huggingface.co/microsoft) |
|
- [License](https://choosealicense.com/licenses/mit/) |
|
|
|
## Recommended Prompt Format (Phi-3) |
|
``` |
|
<|system|> |
|
Provide some context and/or instructions to the model.<|end|> |
|
<|user|> |
|
The user’s message goes here<|end|> |
|
<|assistant|> |
|
AI message goes here<|end|> |
|
<|assistant|> |
|
``` |
|
|
|
Quant Version: [b3405](https://github.com/ggerganov/llama.cpp/releases/tag/b3405) with [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) |
