metadata
pipeline_tag: text-generation
inference: true
widget:
- text: 'def print_hello_world():'
example_title: Hello world
group: Python
license: bigscience-openrail-m
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
metrics:
- code_eval
library_name: transformers
tags:
- code
- TensorBlock
- GGUF
language:
- en
base_model: smallcloudai/Refact-1_6B-fim
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
smallcloudai/Refact-1_6B-fim - GGUF
This repo contains GGUF format model files for smallcloudai/Refact-1_6B-fim.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Our projects
| Awesome MCP Servers | TensorBlock Studio |
|---|---|
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Refact-1_6B-fim-Q2_K.gguf | Q2_K | 0.581 GB | smallest, significant quality loss - not recommended for most purposes |
| Refact-1_6B-fim-Q3_K_S.gguf | Q3_K_S | 0.673 GB | very small, high quality loss |
| Refact-1_6B-fim-Q3_K_M.gguf | Q3_K_M | 0.739 GB | very small, high quality loss |
| Refact-1_6B-fim-Q3_K_L.gguf | Q3_K_L | 0.795 GB | small, substantial quality loss |
| Refact-1_6B-fim-Q4_0.gguf | Q4_0 | 0.857 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Refact-1_6B-fim-Q4_K_S.gguf | Q4_K_S | 0.862 GB | small, greater quality loss |
| Refact-1_6B-fim-Q4_K_M.gguf | Q4_K_M | 0.902 GB | medium, balanced quality - recommended |
| Refact-1_6B-fim-Q5_0.gguf | Q5_0 | 1.030 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Refact-1_6B-fim-Q5_K_S.gguf | Q5_K_S | 1.030 GB | large, low quality loss - recommended |
| Refact-1_6B-fim-Q5_K_M.gguf | Q5_K_M | 1.053 GB | large, very low quality loss - recommended |
| Refact-1_6B-fim-Q6_K.gguf | Q6_K | 1.214 GB | very large, extremely low quality loss |
| Refact-1_6B-fim-Q8_0.gguf | Q8_0 | 1.571 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Refact-1_6B-fim-GGUF --include "Refact-1_6B-fim-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Refact-1_6B-fim-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'