Instructions to use ysn-rfd/Refact-1_6B-fim-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ysn-rfd/Refact-1_6B-fim-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ysn-rfd/Refact-1_6B-fim-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ysn-rfd/Refact-1_6B-fim-GGUF", dtype="auto")

llama-cpp-python

How to use ysn-rfd/Refact-1_6B-fim-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ysn-rfd/Refact-1_6B-fim-GGUF",
	filename="refact-1_6b-fim-q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ysn-rfd/Refact-1_6B-fim-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ysn-rfd/Refact-1_6B-fim-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ysn-rfd/Refact-1_6B-fim-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ysn-rfd/Refact-1_6B-fim-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

SGLang

How to use ysn-rfd/Refact-1_6B-fim-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ysn-rfd/Refact-1_6B-fim-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ysn-rfd/Refact-1_6B-fim-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ysn-rfd/Refact-1_6B-fim-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ysn-rfd/Refact-1_6B-fim-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ysn-rfd/Refact-1_6B-fim-GGUF with Ollama:
```
ollama run hf.co/ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M
```

Unsloth Studio

How to use ysn-rfd/Refact-1_6B-fim-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ysn-rfd/Refact-1_6B-fim-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ysn-rfd/Refact-1_6B-fim-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ysn-rfd/Refact-1_6B-fim-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use ysn-rfd/Refact-1_6B-fim-GGUF with Docker Model Runner:
```
docker model run hf.co/ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M
```

Lemonade

How to use ysn-rfd/Refact-1_6B-fim-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ysn-rfd/Refact-1_6B-fim-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Refact-1_6B-fim-GGUF-Q4_K_M

List all available models

lemonade list

Refact-1_6B-fim-GGUF / README.md

ysn-rfd

Upload README.md with huggingface_hub

c104108 verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

13.7 kB

metadata

base_model: smallcloudai/Refact-1_6B-fim
datasets:
  - bigcode/the-stack-dedup
  - rombodawg/2XUNCENSORED_MegaCodeTraining188k
  - bigcode/commitpackft
language:
  - en
library_name: transformers
license: bigscience-openrail-m
metrics:
  - code_eval
pipeline_tag: text-generation
tags:
  - code
  - llama-cpp
  - matrixportal
inference: true
widget:
  - text: 'def print_hello_world():'
    example_title: Hello world
    group: Python
pretrain-datasets:
  - books
  - arxiv
  - c4
  - falcon-refinedweb
  - wiki
  - github-issues
  - stack_markdown
  - self-made dataset of permissive github code
model-index:
  - name: Refact-1.6B
    results:
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: openai_humaneval
        metrics:
          - type: pass@1
            value: 32
            name: pass@1 (T=0.01)
            verified: false
          - type: pass@1
            value: 31.5
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@10
            value: 53
            name: pass@10 (T=0.8)
            verified: false
          - type: pass@100
            value: 76.9
            name: pass@100 (T=0.8)
            verified: false
      - task:
          type: text-generation
        dataset:
          name: HumanEvalSynthesize Python
          type: bigcode/humanevalpack
        metrics:
          - type: pass@1
            value: 35.8
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 31.6
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 29.1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 26.3
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 18.38
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 12.28
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 15.12
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 13.17
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 2.8
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 26.92
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 26.85
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 30.76
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 25.94
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 8.44
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 26.46
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 17.86
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 20.94
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 18.78
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: -1
            name: pass@1 (T=0.2)
            verified: false
      - task:
          type: text-generation
        dataset:
          name: MBPP
          type: mbpp
        metrics:
          - type: pass@1
            value: 31.15
            name: pass@1 (T=0.01)
            verified: false
      - task:
          type: text-generation
        dataset:
          name: DS-1000 (Overall Completion)
          type: ds1000
        metrics:
          - type: pass@1
            value: 10.1
            name: pass@1 (T=0.2)
            verified: false
      - task:
          type: text-generation
        dataset:
          name: MultiPL-HumanEval (C++)
          type: nuprl/MultiPL-E
        metrics:
          - type: pass@1
            value: 21.61
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 13.91
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 9.5
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 53.57
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 21.58
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 13.75
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 26.88
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 15.26
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 23.04
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 12.1
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 29.6
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 13.77
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 12.68
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 4.29
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 19.54
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 18.33
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 5.7
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 17.68
            name: pass@1 (T=0.2)
            verified: false
          - type: pass@1
            value: 25
            name: pass@1 (T=0.2)
            verified: false

ysn-rfd/Refact-1_6B-fim-GGUF

This model was converted to GGUF format from smallcloudai/Refact-1_6B-fim using llama.cpp via the ggml.ai's all-gguf-same-where space. Refer to the original model card for more details on the model.

✅ Quantized Models Download List

🔍 Recommended Quantizations

✨ General CPU Use: Q4_K_M (Best balance of speed/quality)
📱 ARM Devices: Q4_0 (Optimized for ARM CPUs)
🏆 Maximum Quality: Q8_0 (Near-original quality)

📦 Full Quantization Options

🚀 Download	🔢 Type	📝 Notes
Download		Basic quantization
Download		Small size
Download		Balanced quality
Download		Better quality
Download		Fast on ARM
Download		Fast, recommended
Download	⭐	Best balance
Download		Good quality
Download		Balanced
Download		High quality
Download	🏆	Very good quality
Download	⚡	Fast, best quality
Download		Maximum accuracy

💡 Tip: Use F16 for maximum precision when quality is critical

🚀 Applications and Tools for Locally Quantized LLMs

🖥️ Desktop Applications

Application	Description	Download Link
Llama.cpp	A fast and efficient inference engine for GGUF models.	GitHub Repository
Ollama	A streamlined solution for running LLMs locally.	Website
AnythingLLM	An AI-powered knowledge management tool.	GitHub Repository
Open WebUI	A user-friendly web interface for running local LLMs.	GitHub Repository
GPT4All	A user-friendly desktop application supporting various LLMs, compatible with GGUF models.	GitHub Repository
LM Studio	A desktop application designed to run and manage local LLMs, supporting GGUF format.	Website
GPT4All Chat	A chat application compatible with GGUF models for local, offline interactions.	GitHub Repository

📱 Mobile Applications

Application	Description	Download Link
ChatterUI	A simple and lightweight LLM app for mobile devices.	GitHub Repository
Maid	Mobile Artificial Intelligence Distribution for running AI models on mobile devices.	GitHub Repository
PocketPal AI	A mobile AI assistant powered by local models.	GitHub Repository
Layla	A flexible platform for running various AI models on mobile devices.	Website

🎨 Image Generation Applications

Application	Description	Download Link
Stable Diffusion	An open-source AI model for generating images from text.	GitHub Repository
Stable Diffusion WebUI	A web application providing access to Stable Diffusion models via a browser interface.	GitHub Repository
Local Dream	Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference.	GitHub Repository
Stable-Diffusion-Android (SDAI)	An open-source AI art application for Android devices, enabling digital art creation.	GitHub Repository