commit 5fbd840a0dae15aac798343074f736cda8cef458 Author: ModelHub XC Date: Wed Apr 22 21:49:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ysn-rfd/Refact-1_6B-fim-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..02f6710 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +refact-1_6b-fim-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +refact-1_6b-fim-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +refact-1_6b-fim-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +refact-1_6b-fim-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +refact-1_6b-fim-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3714ee2 --- /dev/null +++ b/README.md @@ -0,0 +1,347 @@ +--- +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: 32.0 + 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: 53.0 + 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`](https://huggingface.co/smallcloudai/Refact-1_6B-fim) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space. +Refer to the [original model card](https://huggingface.co/smallcloudai/Refact-1_6B-fim) for more details on the model. + +## ✅ Quantized Models Download List + +### 🔍 Recommended Quantizations +- **✨ General CPU Use:** [`Q4_K_M`](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q4_k_m.gguf) (Best balance of speed/quality) +- **📱 ARM Devices:** [`Q4_0`](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q4_0.gguf) (Optimized for ARM CPUs) +- **🏆 Maximum Quality:** [`Q8_0`](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q8_0.gguf) (Near-original quality) + +### 📦 Full Quantization Options +| 🚀 Download | 🔢 Type | 📝 Notes | +|:---------|:-----|:------| +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q2_k.gguf) | ![Q2_K](https://img.shields.io/badge/Q2_K-1A73E8) | Basic quantization | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q3_k_s.gguf) | ![Q3_K_S](https://img.shields.io/badge/Q3_K_S-34A853) | Small size | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q3_k_m.gguf) | ![Q3_K_M](https://img.shields.io/badge/Q3_K_M-FBBC05) | Balanced quality | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q3_k_l.gguf) | ![Q3_K_L](https://img.shields.io/badge/Q3_K_L-4285F4) | Better quality | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q4_0.gguf) | ![Q4_0](https://img.shields.io/badge/Q4_0-EA4335) | Fast on ARM | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q4_k_s.gguf) | ![Q4_K_S](https://img.shields.io/badge/Q4_K_S-673AB7) | Fast, recommended | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q4_k_m.gguf) | ![Q4_K_M](https://img.shields.io/badge/Q4_K_M-673AB7) ⭐ | Best balance | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q5_0.gguf) | ![Q5_0](https://img.shields.io/badge/Q5_0-FF6D01) | Good quality | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q5_k_s.gguf) | ![Q5_K_S](https://img.shields.io/badge/Q5_K_S-0F9D58) | Balanced | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q5_k_m.gguf) | ![Q5_K_M](https://img.shields.io/badge/Q5_K_M-0F9D58) | High quality | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q6_k.gguf) | ![Q6_K](https://img.shields.io/badge/Q6_K-4285F4) 🏆 | Very good quality | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality | +| [Download](https://huggingface.co/ysn-rfd/Refact-1_6B-fim-GGUF/resolve/main/refact-1_6b-fim-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | 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](https://github.com/ggml-org/llama.cpp) | +| **Ollama** | A streamlined solution for running LLMs locally. | [Website](https://ollama.com/) | +| **AnythingLLM** | An AI-powered knowledge management tool. | [GitHub Repository](https://github.com/Mintplex-Labs/anything-llm) | +| **Open WebUI** | A user-friendly web interface for running local LLMs. | [GitHub Repository](https://github.com/open-webui/open-webui) | +| **GPT4All** | A user-friendly desktop application supporting various LLMs, compatible with GGUF models. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) | +| **LM Studio** | A desktop application designed to run and manage local LLMs, supporting GGUF format. | [Website](https://lmstudio.ai/) | +| **GPT4All Chat**| A chat application compatible with GGUF models for local, offline interactions. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) | + +--- + +## 📱 Mobile Applications + +| Application | Description | Download Link | +|-------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------| +| **ChatterUI** | A simple and lightweight LLM app for mobile devices. | [GitHub Repository](https://github.com/Vali-98/ChatterUI) | +| **Maid** | Mobile Artificial Intelligence Distribution for running AI models on mobile devices. | [GitHub Repository](https://github.com/Mobile-Artificial-Intelligence/maid) | +| **PocketPal AI** | A mobile AI assistant powered by local models. | [GitHub Repository](https://github.com/a-ghorbani/pocketpal-ai) | +| **Layla** | A flexible platform for running various AI models on mobile devices. | [Website](https://www.layla-network.ai/) | + +--- + +## 🎨 Image Generation Applications + +| Application | Description | Download Link | +|-------------------------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------| +| **Stable Diffusion** | An open-source AI model for generating images from text. | [GitHub Repository](https://github.com/CompVis/stable-diffusion) | +| **Stable Diffusion WebUI** | A web application providing access to Stable Diffusion models via a browser interface. | [GitHub Repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui) | +| **Local Dream** | Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference. | [GitHub Repository](https://github.com/xororz/local-dream) | +| **Stable-Diffusion-Android (SDAI)** | An open-source AI art application for Android devices, enabling digital art creation. | [GitHub Repository](https://github.com/ShiftHackZ/Stable-Diffusion-Android) | + +--- + diff --git a/refact-1_6b-fim-q4_k_m.gguf b/refact-1_6b-fim-q4_k_m.gguf new file mode 100644 index 0000000..42a7b1b --- /dev/null +++ b/refact-1_6b-fim-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7388474b0732e55689d0057198765c66d49f291c5ecb547311ae9278b95ee07f +size 968338784 diff --git a/refact-1_6b-fim-q5_0.gguf b/refact-1_6b-fim-q5_0.gguf new file mode 100644 index 0000000..3d1b690 --- /dev/null +++ b/refact-1_6b-fim-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ed4433b33fd8931394463e08de1684050c065aeb517f57a37740eaee7bd110 +size 1105833312 diff --git a/refact-1_6b-fim-q5_k_m.gguf b/refact-1_6b-fim-q5_k_m.gguf new file mode 100644 index 0000000..7415d6b --- /dev/null +++ b/refact-1_6b-fim-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:229de8b3304e4a99aaf735d1367f343def972043051ced63c0f862df5d2873f1 +size 1130622304 diff --git a/refact-1_6b-fim-q6_k.gguf b/refact-1_6b-fim-q6_k.gguf new file mode 100644 index 0000000..58841a6 --- /dev/null +++ b/refact-1_6b-fim-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755560573e1d7b1888a9e7acf0d3eff941560dc01387452d4b98393a7d68d985 +size 1303048544 diff --git a/refact-1_6b-fim-q8_0.gguf b/refact-1_6b-fim-q8_0.gguf new file mode 100644 index 0000000..4db7bbd --- /dev/null +++ b/refact-1_6b-fim-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b24c024b673ff01418c6011a85e1999e400d777fb42ec5300aee0bf1c14f86 +size 1687087456