commit 8a96396aad862f48cacd1100073297e550c73827 Author: ModelHub XC Date: Wed Sep 2 01:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: CelesteImperia/Gemma-2-2B-IT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c009a96 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.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 +gemma2_2b_q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-2B-IT-Platinum-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-2B-IT-Platinum-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-2B-IT-Platinum-F16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-2B-IT-Platinum-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-2B-IT-Platinum-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-2-2B-IT-Platinum-F16.gguf b/Gemma-2-2B-IT-Platinum-F16.gguf new file mode 100644 index 0000000..dc27f87 --- /dev/null +++ b/Gemma-2-2B-IT-Platinum-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cebf46b5e4aef6b65fe3e24c76d32193319464f6c59129b40040b2369ec785a +size 5235214208 diff --git a/Gemma-2-2B-IT-Platinum-Q4_K_M.gguf b/Gemma-2-2B-IT-Platinum-Q4_K_M.gguf new file mode 100644 index 0000000..7fbd57f --- /dev/null +++ b/Gemma-2-2B-IT-Platinum-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a98a17646833d53553098ef40dda1c26783c4ae0d09197cabb6c05fbe8d81f +size 1708582784 diff --git a/Gemma-2-2B-IT-Platinum-Q5_K_M.gguf b/Gemma-2-2B-IT-Platinum-Q5_K_M.gguf new file mode 100644 index 0000000..8b94f35 --- /dev/null +++ b/Gemma-2-2B-IT-Platinum-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113f0bddd18d68672e80d10b74ed131aa04b7389520dcdf61ef94c126c014fd2 +size 1923278720 diff --git a/Gemma-2-2B-IT-Platinum-Q6_K.gguf b/Gemma-2-2B-IT-Platinum-Q6_K.gguf new file mode 100644 index 0000000..4e52a8b --- /dev/null +++ b/Gemma-2-2B-IT-Platinum-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88690a23068a68e794bf8481e3ae5b9f0496147b8d8fee51a96157cfb27c11f6 +size 2151393152 diff --git a/Gemma-2-2B-IT-Platinum-Q8_0.gguf b/Gemma-2-2B-IT-Platinum-Q8_0.gguf new file mode 100644 index 0000000..5681d4e --- /dev/null +++ b/Gemma-2-2B-IT-Platinum-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:239de574b3bc969eac5e3d2d21f0c6861aa4cd6aac0b4c7a7176232680702f09 +size 2784495488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be7186c --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: google/gemma-2-2b-it +library_name: gguf +pipeline_tag: text-generation +license: gemma +tags: +- gguf +- llama-cpp +- gemma-2 +- celeste-imperia +--- + +# Gemma-2-2B-IT-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 **Universal GGUF** release of **Gemma-2-2B-Instruct**. This collection provides multiple quantization levels to support everything from high-VRAM workstations to mobile and edge devices. + +## 📦 Available Files & Quantization Details + +| File Name | Quantization | Size | Accuracy | Recommended For | +| :--- | :--- | :--- | :--- | :--- | +| **Gemma-2-2B-IT-Platinum-F16.gguf** | FP16 | ~5.2 GB | 100% | Master Reference / Benchmarking | +| **Gemma-2-2B-IT-Platinum-Q8_0.gguf** | Q8_0 | ~2.7 GB | 99.9% | Platinum Reference / High-Fidelity | +| **Gemma-2-2B-IT-Platinum-Q6_K.gguf** | Q6_K | ~2.1 GB | 99.5% | High-end GPU / Complex Reasoning | +| **Gemma-2-2B-IT-Platinum-Q5_K_M.gguf** | Q5_K_M | ~1.8 GB | 99.0% | Balanced Desktop Performance | +| **Gemma-2-2B-IT-Platinum-Q4_K_M.gguf** | Q4_K_M | ~1.5 GB | 98.2% | Mobile / Low-VRAM / Efficiency | + +--- + +## 🐍 Python Inference (llama-cpp-python) + +To run these engines using Python: + +```python +from llama_cpp import Llama + +llm = Llama( + model_path="Gemma-2-2B-IT-Platinum-Q8_0.gguf", + n_gpu_layers=-1, # Target all layers to NVIDIA/Apple GPU + n_ctx=2048 +) + +output = llm("Explain the architecture of Gemma 2.", max_tokens=200) +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("Gemma-2-2B-IT-Platinum-Q8_0.gguf") { + ContextSize = 2048, + 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:** Gemma-2 +- **Hardware Validation:** RTX 3090 + RTX A4000 + +--- + +### ☕ Support the Forge + +Maintaining a high-capacity local AI warehouse with full-fidelity weights requires significant hardware resources. If these models power your industrial projects or research, 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/gemma2_2b_q4_k_m.gguf b/gemma2_2b_q4_k_m.gguf new file mode 100644 index 0000000..7959b9f --- /dev/null +++ b/gemma2_2b_q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02925fba7b7b96fcbe6272a10f2a5e4218c74f867a0d542bebe89232615cfb3 +size 1708582784 diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..656f61c --- /dev/null +++ b/requirements.txt @@ -0,0 +1,8 @@ +# GGUF Conversion & Inference +llama-cpp-python +sentencepiece +gguf +transformers>=4.45.0 +protobuf +# Optional: For faster conversion on some architectures +numpy<2.0.0 \ No newline at end of file