commit 18c41a063a20985c38c57bc74c46bce66ba97a37 Author: ModelHub XC Date: Fri Jun 19 04:39:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: McaTech/Nonet Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eaa9ed1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,9 @@ +ChatNONET4.apk filter=lfs diff=lfs merge=lfs -text +arm64-v8a/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +armeabi-v7a/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +x86/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +x86_64/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +Precompiled_Binaries_Android/jniLibs/arm64-v8a/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +Precompiled_Binaries_Android/jniLibs/armeabi-v7a/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +Precompiled_Binaries_Android/jniLibs/x86_64/libllama_cli.so filter=lfs diff=lfs merge=lfs -text +Precompiled_Binaries_Android/jniLibs/x86/libllama_cli.so filter=lfs diff=lfs merge=lfs -text diff --git a/ChatNONET-135m-tuned-q8_0.gguf b/ChatNONET-135m-tuned-q8_0.gguf new file mode 100644 index 0000000..62249a5 --- /dev/null +++ b/ChatNONET-135m-tuned-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94db9834ae2c4e26b54ff46cbf70dbb9685972a2bcaaf60034bcb655b8ea1984 +size 144811552 diff --git a/ChatNONET-1B-tuned-q8_0.gguf b/ChatNONET-1B-tuned-q8_0.gguf new file mode 100644 index 0000000..11d7812 --- /dev/null +++ b/ChatNONET-1B-tuned-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d4a25c675cabdbb385719173e5f7d350286942b8fd4fb2e54f499b3bd88b3b +size 1321082592 diff --git a/ChatNONET-300m-tuned-q8_0.gguf b/ChatNONET-300m-tuned-q8_0.gguf new file mode 100644 index 0000000..80d308c --- /dev/null +++ b/ChatNONET-300m-tuned-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052a16bbff92852809dd3a822b1f412b2322ed2344b2de78bf7232911304acda +size 386405824 diff --git a/ChatNONET-3B-tuned-q8_0.gguf b/ChatNONET-3B-tuned-q8_0.gguf new file mode 100644 index 0000000..ba6293e --- /dev/null +++ b/ChatNONET-3B-tuned-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09ac1d25e5497a1e046699cd2dfc631e37f237f5fbb0301264bad750dd86e1d +size 3421898912 diff --git a/ChatNONET4.apk b/ChatNONET4.apk new file mode 100644 index 0000000..2c63862 --- /dev/null +++ b/ChatNONET4.apk @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f278ffa7661b6af4ee3b66a4ea1bf36af7124fa1142c2e02792d38d3e697f1de +size 11355104 diff --git a/Precompiled_Binaries_Android/jniLibs/arm64-v8a/libllama_cli.so b/Precompiled_Binaries_Android/jniLibs/arm64-v8a/libllama_cli.so new file mode 100644 index 0000000..35307f1 --- /dev/null +++ b/Precompiled_Binaries_Android/jniLibs/arm64-v8a/libllama_cli.so @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd326c43090074ddc1cd9104f50ed7a0a44fcbf7744237993de14c65d9c9263 +size 31600448 diff --git a/Precompiled_Binaries_Android/jniLibs/armeabi-v7a/libllama_cli.so b/Precompiled_Binaries_Android/jniLibs/armeabi-v7a/libllama_cli.so new file mode 100644 index 0000000..a9d1e6f --- /dev/null +++ b/Precompiled_Binaries_Android/jniLibs/armeabi-v7a/libllama_cli.so @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7172346db96835584efe2f4628831a84f3e3b7191f14f0e2eff85c2abf34045 +size 26663752 diff --git a/Precompiled_Binaries_Android/jniLibs/x86/libllama_cli.so b/Precompiled_Binaries_Android/jniLibs/x86/libllama_cli.so new file mode 100644 index 0000000..114620d --- /dev/null +++ b/Precompiled_Binaries_Android/jniLibs/x86/libllama_cli.so @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ee17daa25f80c6351505fad9f5989fe0b918b20d64766cc70856a386cf3659 +size 31522288 diff --git a/Precompiled_Binaries_Android/jniLibs/x86_64/libllama_cli.so b/Precompiled_Binaries_Android/jniLibs/x86_64/libllama_cli.so new file mode 100644 index 0000000..114620d --- /dev/null +++ b/Precompiled_Binaries_Android/jniLibs/x86_64/libllama_cli.so @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ee17daa25f80c6351505fad9f5989fe0b918b20d64766cc70856a386cf3659 +size 31522288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5640ef3 --- /dev/null +++ b/README.md @@ -0,0 +1,119 @@ + +--- +license: apache-2.0 +language: + - en +library_name: llama.cpp +tags: + - gguf + - quantized + - int8 + - offline-ai + - local-llm + - chatnonet +model_type: causal +inference: true +pipeline_tag: text-generation +--- + +# NONET + +**NONET** is a family of **offline**, quantized large language models fine-tuned for **question answering** with **direct, concise answers**. Designed for local execution using `llama.cpp`, NONET is available in multiple sizes and optimized for Android or Python-based environments. + +## Model Details + +### Model Description + +NONET is intended for lightweight offline use, particularly on local devices like mobile phones or single-board computers. The models have been **fine-tuned for direct-answer QA** and quantized to **int8 (q8_0)** using `llama.cpp`. + +| Model Name | Base Model | Size | +|----------------------------------|--------------------|--------| +| ChatNONET-135m-tuned-q8_0.gguf | Smollm | 135M | +| ChatNONET-300m-tuned-q8_0.gguf | Smollm | 300M | +| ChatNONET-1B-tuned-q8_0.gguf | LLaMA 3.2 | 1B | +| ChatNONET-3B-tuned-q8_0.gguf | LLaMA 3.2 | 3B | + +- **Developed by:** McaTech (Michael Cobol Agan) +- **Model type:** Causal decoder-only transformer +- **Languages:** English +- **License:** Apache 2.0 +- **Finetuned from:** + - Smollm (135M, 300M variants) + - LLaMA 3.2 (1B, 3B variants) + +## Uses + +### Direct Use + +- Offline QA chatbot +- Local assistants (no internet required) +- Embedded Android or Python apps + +### Out-of-Scope Use + +- Long-form text generation +- Tasks requiring real-time web access +- Creative storytelling or coding tasks + +## Bias, Risks, and Limitations + +NONET may reproduce biases present in its base models or fine-tuning data. Outputs should not be relied upon for sensitive or critical decisions. + +### Recommendations + +- Validate important responses +- Choose model size based on your device capability +- Avoid over-reliance for personal or legal advice + +## How to Get Started with the Model +### For Android Devices +- Try the **Android app** in my **Github**: [Download ChatNONET APK](https://github.com/Mca-Tech/ChatNONET) +### You can also build llama.cpp your own and run it +```bash +# Clone llama.cpp and build it +git clone https://github.com/ggerganov/llama.cpp +cd llama.cpp +make + +# Run the model +./llama-cli -m ./ChatNONET-300m-tuned-q8_0.gguf -p "You are ChatNONET AI assistant." -cnv +```` + +## Training Details + +* **Finetuning Goal:** Direct-answer question answering +* **Precision:** FP16 mixed precision +* **Frameworks:** PyTorch, Transformers, Bitsandbytes +* **Quantization:** int8 GGUF (`q8_0`) via `llama.cpp` + +## Evaluation + +* Evaluated internally on short QA prompts +* Capable of direct factual or logical answers +* Larger models perform better on reasoning tasks + +## Technical Specifications + +* **Architecture:** + + * Smollm (135M, 300M) + * LLaMA 3.2 (1B, 3B) +* **Format:** GGUF +* **Quantization:** q8\_0 (int8) +* **Deployment:** Mobile (Android) and desktop via `llama.cpp` + +## Citation + +```bibtex +@misc{chatnonet2025, + title={ChatNONET: Offline Quantized Q&A Models}, + author={Michael Cobol Agan}, + year={2025}, + note={\url{https://huggingface.co/McaTech/Nonet}}, +} +``` + +## Contact + +* **Author:** Michael Cobol Agan (McaTech) +* **Facebook:** [FB Profile](https://www.facebook.com/michael.cobol.agan.2025/)