commit e1d9765028a2522027b2edf46055bd93e95ab3e3 Author: ModelHub XC Date: Tue May 5 21:25:31 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: CelesteImperia/Phi-3.5-mini-instruct-Platinum-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce80033 --- /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 +Phi-3.5-mini-instruct-Platinum-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-Platinum-F16.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-Platinum-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-Platinum-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-Platinum-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..705e612 --- /dev/null +++ b/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2024 Microsoft + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. \ No newline at end of file diff --git a/Phi-3.5-mini-instruct-Platinum-F16.gguf b/Phi-3.5-mini-instruct-Platinum-F16.gguf new file mode 100644 index 0000000..4346ad2 --- /dev/null +++ b/Phi-3.5-mini-instruct-Platinum-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfb7f35ff9b60e406728c99bf6247454ebe51218766371e9381a995547cffba3 +size 7643297280 diff --git a/Phi-3.5-mini-instruct-Platinum-Q4_K_M.gguf b/Phi-3.5-mini-instruct-Platinum-Q4_K_M.gguf new file mode 100644 index 0000000..2b6df5c --- /dev/null +++ b/Phi-3.5-mini-instruct-Platinum-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5347cbd620330a7c051c3d2fcad156b2c606340682f3d09c92df5bcfb9deaba +size 2396771328 diff --git a/Phi-3.5-mini-instruct-Platinum-Q5_K_M.gguf b/Phi-3.5-mini-instruct-Platinum-Q5_K_M.gguf new file mode 100644 index 0000000..6404736 --- /dev/null +++ b/Phi-3.5-mini-instruct-Platinum-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e90a70f0c3832dd90e86e6df179446d51d94bdfa6934eee42bd8e892f8b9965 +size 2755113984 diff --git a/Phi-3.5-mini-instruct-Platinum-Q6_K.gguf b/Phi-3.5-mini-instruct-Platinum-Q6_K.gguf new file mode 100644 index 0000000..2f16170 --- /dev/null +++ b/Phi-3.5-mini-instruct-Platinum-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567330ee02f1d18c5bbaacf12984e57dcd9c5cdffad20be988f0154e362e50fd +size 3135853056 diff --git a/Phi-3.5-mini-instruct-Platinum-Q8_0.gguf b/Phi-3.5-mini-instruct-Platinum-Q8_0.gguf new file mode 100644 index 0000000..021002e --- /dev/null +++ b/Phi-3.5-mini-instruct-Platinum-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe6b9881e856dcb0fb33fede9b4b24c88f6a07592aa4f66568aa38d29a14153 +size 4061222400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2806ef3 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: microsoft/Phi-3.5-mini-instruct +library_name: gguf +pipeline_tag: text-generation +license: mit +tags: +- gguf +- llama-cpp +- phi-3.5 +- celeste-imperia +--- + +# Phi-3.5-mini-instruct-GGUF (Platinum Series) + +![Status](https://img.shields.io/badge/Status-Active-success) +![Format](https://img.shields.io/badge/Format-GGUF-green) +![Series](https://img.shields.io/badge/Series-Platinum-silver) +[![Support](https://img.shields.io/badge/Support-Razorpay-orange)](https://razorpay.me/@huggingface) + +This repository contains the **Platinum Series** universal GGUF release of **Phi-3.5-mini-instruct**. This collection provides multiple quantization levels optimized for cross-platform performance, offering advanced reasoning capabilities with 128k context support. + +## 📦 Available Files & Quantization Details + +| File Name | Quantization | Size | Accuracy | Recommended For | +| :--- | :--- | :--- | :--- | :--- | +| **Phi-3.5-mini-instruct-Platinum-F16.gguf** | FP16 | ~7.6 GB | 100% | Master Reference / Benchmarking | +| **Phi-3.5-mini-instruct-Platinum-Q8_0.gguf** | Q8_0 | ~4.1 GB | 99.9% | Platinum Reference / High-Fidelity | +| **Phi-3.5-mini-instruct-Platinum-Q6_K.gguf** | Q6_K | ~3.1 GB | 99.8% | High-Quality Inference | +| **Phi-3.5-mini-instruct-Platinum-Q5_K_M.gguf** | Q5_K_M | ~2.8 GB | 99.4% | Balanced Desktop Performance | +| **Phi-3.5-mini-instruct-Platinum-Q4_K_M.gguf** | Q4_K_M | ~2.4 GB | 98.8% | Mobile / Low-Power Efficiency | + +--- + +## 🐍 Python Inference (llama-cpp-python) + +To run these engines using Python: + +```python +from llama_cpp import Llama + +llm = Llama( + model_path="Phi-3.5-mini-instruct-Platinum-Q8_0.gguf", + n_gpu_layers=-1, # Target all layers to NVIDIA/Apple GPU + n_ctx=4096 +) + +output = llm("Discuss the architectural benefits of Phi-3.5.", max_tokens=150) +print(output["choices"][0]["text"]) +``` + +--- + +## 💻 For C# / .NET Users (LLamaSharp) + +This collection is fully compatible with .NET applications via the ``LLamaSharp`` library. + +```csharp +using LLama.Common; +using LLama; + +var parameters = new ModelParams("Phi-3.5-mini-instruct-Platinum-Q8_0.gguf") { + ContextSize = 4096, + GpuLayerCount = 35 +}; + +using var model = LLamaWeights.LoadFromFile(parameters); +using var context = model.CreateContext(parameters); +var executor = new InteractiveExecutor(context); + +Console.WriteLine("Universal Engine Active."); +``` + +--- + +## 🏗️ Technical Details +- **Optimization Tool:** llama.cpp (CUDA-accelerated) +- **Architecture:** Phi-3.5 +- **Hardware Validation:** Dual-GPU (RTX 3090 + RTX A4000) + +--- + +### ☕ Support the Forge + +Maintaining the production line for high-fidelity models requires significant hardware resources. If these tools power your research or industrial projects, please consider supporting the development: + +| Platform | Support Link | +| :--- | :--- | +| **Global & India** | [Support via Razorpay](https://razorpay.me/@huggingface) | + +**Scan to support via UPI (India Only):** + + + +--- + +**Connect with the architect:** [Abhishek Jaiswal on LinkedIn](https://www.linkedin.com/in/abhishek-jaiswal-524056a/) \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..86c375f --- /dev/null +++ b/requirements.txt @@ -0,0 +1,4 @@ +optimum-intel[openvino,nncf]>=1.20.0 +transformers>=4.45.0 +accelerate +sentencepiece \ No newline at end of file