Model Intelligence Sheet
oblivious/refact-1.6b-fim-gguf overview
Refact-1.6B-fim-GGUF
Downloads
398
Likes
4
Pipeline
text-generation
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
14 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| refact-1_6b-Q2_K.gguf | GGUF | Q2_K | 666.34 MB | Download |
| refact-1_6b-Q3_K_L.gguf | GGUF | Q3_K_L | 814.29 MB | Download |
| refact-1_6b-Q3_K_M.gguf | GGUF | Q3_K_M | 756.57 MB | Download |
| refact-1_6b-Q3_K_S.gguf | GGUF | Q3_K_S | 689.51 MB | Download |
| refact-1_6b-Q4_0.gguf | GGUF | — | 877.59 MB | Download |
| refact-1_6b-Q4_1.gguf | GGUF | — | 966.10 MB | Download |
| refact-1_6b-Q4_K_M.gguf | GGUF | Q4_K_M | 923.48 MB | Download |
| refact-1_6b-Q4_K_S.gguf | GGUF | Q4_K_S | 883.15 MB | Download |
| refact-1_6b-Q5_0.gguf | GGUF | — | 1.03 GB | Download |
| refact-1_6b-Q5_1.gguf | GGUF | — | 1.12 GB | Download |
| refact-1_6b-Q5_K_M.gguf | GGUF | Q5_K_M | 1.05 GB | Download |
| refact-1_6b-Q5_K_S.gguf | GGUF | Q5_K_S | 1.03 GB | Download |
| refact-1_6b-Q6_K.gguf | GGUF | Q6_K | 1.21 GB | Download |
| refact-1_6b-Q8_0.gguf | GGUF | — | 1.57 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"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"
],
"frontmatter": {
"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": [
"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"
]
},
"hero_image_url": "",
"summary": "# Refact-1.6B-fim-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: smallcloudai/Refact-1_6B-fim\nlicense: bigscience-openrail-m\nmodel_creator: Small Magellanic Cloud AI\nmodel_name: Refact-1.6B\npipeline_tag: text-generation\nprompt_template: '<fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>'\npretrain-datasets:\n- books\n- arxiv\n- c4\n- falcon-refinedweb\n- wiki\n- github-issues\n- stack_markdown\n- self-made dataset of permissive github code\ndatasets:\n- bigcode/the-stack-dedup\n- rombodawg/2XUNCENSORED_MegaCodeTraining188k\n- bigcode/commitpackft\ntags:\n- code\nlanguage:\n- en\n---\n# Refact-1.6B-fim-GGUF\n- Model creator: [Small Magellanic Cloud AI](https://huggingface.co/smallcloudai)\n- Original model: [Refact-1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim)\n\n\n## Description\nThis repository contains quantized GGUF format model files for [Refact-1.6B](https://huggingface.co/smallcloudai/Refact-1_6B-fim).\n\n\n## Prompt: fill in the middle\n```\n<fim_prefix>def print_hello_world():\\n \"\"\"<fim_suffix>\\n print(\"Hello world!\")<fim_middle>\n```\n\n\n## Prompt: chat (experimental)\n```\n<empty_output>SYSTEM You are a programming assistant\n<empty_output>USER How do I sort a list in Python?\n<empty_output>ASSISTANT\n```\n\n\n## Example `llama.cpp` command\n```shell\n./main -m refact-1_6b-Q4_K_M.gguf -c 4096 -n -1 -p '<fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>'\n```\nFor other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)\n",
"related_quantizations": []
},
"tags": [
"gguf",
"code",
"text-generation",
"en",
"dataset:bigcode/the-stack-dedup",
"dataset:rombodawg/2XUNCENSORED_MegaCodeTraining188k",
"dataset:bigcode/commitpackft",
"base_model:refactai/Refact-1_6B-fim",
"base_model:quantized:refactai/Refact-1_6B-fim",
"license:bigscience-openrail-m",
"endpoints_compatible",
"region:us"
],
"likes": 4,
"downloads": 398,
"gated": false,
"private": false,
"last_modified": "2023-11-01T18:13:32.000Z",
"created_at": "2023-11-01T17:20:10.000Z",
"pipeline_tag": "text-generation",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "654288ca21f55472a89ba9ec",
"id": "oblivious/Refact-1.6B-fim-GGUF",
"modelId": "oblivious/Refact-1.6B-fim-GGUF",
"sha": "b7f7deb2cdb47de16f808d9c334b9b34e10543f6",
"createdAt": "2023-11-01T17:20:10.000Z",
"lastModified": "2023-11-01T18:13:32.000Z",
"author": "oblivious",
"downloads": 398,
"likes": 4,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "",
"siblings_count": 16
}