Hugging Face's logo

oblivious
/
Refact-1.6B-fim-GGUF

Text Generation
GGUF
English
code
Inference Endpoints
Model card Files Community
Refact-1.6B-fim-GGUF / README.md
IDDT
Add metadata.
b7f7deb
preview code
|
raw
history blame contribute delete
1.49 kB
metadata
base_model: smallcloudai/Refact-1_6B-fim
license: bigscience-openrail-m
model_creator: Small Magellanic Cloud AI
model_name: Refact-1.6B
pipeline_tag: text-generation
prompt_template: <fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>
pretrain-datasets:
  - books
  - arxiv
  - c4
  - falcon-refinedweb
  - wiki
  - github-issues
  - stack_markdown
  - self-made dataset of permissive github code
datasets:
  - bigcode/the-stack-dedup
  - rombodawg/2XUNCENSORED_MegaCodeTraining188k
  - bigcode/commitpackft
tags:
  - code
language:
  - en

Refact-1.6B-fim-GGUF

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