Downloads · 30 days
199
3% of all-time downloads
Refact-1.6B-fim-GGUF
oblivious/Refact-1.6B-fim-GGUF
Refact-1.6B-fim-GGUF is a text generation model from oblivious. Use it when you need the model to write or continue text. The card lists the license as bigscience-openrail-m.
- Model creator: Small Magellanic Cloud AI - Original model: Refact-1.6B
All-time downloads
6.1K
Public
Repo size
14.4 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.gguf14.4 GB · 100%
At a glance
- Task
- Text Generation
- License
- bigscience-openrail-m
- Access
- Public
- Created
- Nov 1, 2023
- Updated
- Nov 1, 2023
- SHA
- b7f7deb2
Try a prompt
Base models
Model card
From the Hugging Face model README
Refact-1.6B-fim-GGUF
- Model creator: Small Magellanic Cloud AI
- Original model: Refact-1.6B
Description
This repository contains quantized GGUF format model files for Refact-1.6B.
Prompt: fill in the middle
<fim_prefix>def print_hello_world():\n """<fim_suffix>\n print("Hello world!")<fim_middle>
Prompt: chat (experimental)
<empty_output>SYSTEM You are a programming assistant
<empty_output>USER How do I sort a list in Python?
<empty_output>ASSISTANT
Example llama.cpp command
./main -m refact-1_6b-Q4_K_M.gguf -c 4096 -n -1 -p '<fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>'
For other parameters and how to use them, please refer to the llama.cpp documentation
- Task
- Text Generation
- License
- bigscience-openrail-m
- Languages
- en
- Created
- Nov 1, 2023
- Updated
- Nov 1, 2023