commit b5775255794d4605afb67de3adb4301a88628cc9 Author: ModelHub XC Date: Mon Nov 2 22:09:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaziyarPanahi/gemma-3-1b-thinking-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a961bf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +gemma-3-1b-thinking-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-thinking-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-thinking-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-thinking-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-thinking-v2.fp16.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..28a9265 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: vinhnx90/gemma-3-1b-thinking-v2 +inference: false +model_creator: vinhnx90 +model_name: gemma-3-1b-thinking-v2-GGUF +pipeline_tag: text-generation +quantized_by: MaziyarPanahi +tags: +- quantized +- 2-bit +- 3-bit +- 4-bit +- 5-bit +- 6-bit +- 8-bit +- GGUF +- text-generation +--- +# [MaziyarPanahi/gemma-3-1b-thinking-v2-GGUF](https://huggingface.co/MaziyarPanahi/gemma-3-1b-thinking-v2-GGUF) +- Model creator: [vinhnx90](https://huggingface.co/vinhnx90) +- Original model: [vinhnx90/gemma-3-1b-thinking-v2](https://huggingface.co/vinhnx90/gemma-3-1b-thinking-v2) + +## Description +[MaziyarPanahi/gemma-3-1b-thinking-v2-GGUF](https://huggingface.co/MaziyarPanahi/gemma-3-1b-thinking-v2-GGUF) contains GGUF format model files for [vinhnx90/gemma-3-1b-thinking-v2](https://huggingface.co/vinhnx90/gemma-3-1b-thinking-v2). + +### About GGUF + +GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. + +Here is an incomplete list of clients and libraries that are known to support GGUF: + +* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. +* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. +* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. +* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. +* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. +* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. +* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. +* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. +* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. +* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. + +## Special thanks + +🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..9f0f76f --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "mistral" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/gemma-3-1b-thinking-v2.Q5_K_M.gguf b/gemma-3-1b-thinking-v2.Q5_K_M.gguf new file mode 100644 index 0000000..4b2beae --- /dev/null +++ b/gemma-3-1b-thinking-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a36f654994e73a9ec4040e5ffe1efe5be1ab359d86b05a5f90448366933f2ba2 +size 851346112 diff --git a/gemma-3-1b-thinking-v2.Q5_K_S.gguf b/gemma-3-1b-thinking-v2.Q5_K_S.gguf new file mode 100644 index 0000000..b83fb90 --- /dev/null +++ b/gemma-3-1b-thinking-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c759703fc1d9559f4600af23c804ddc4168ae1ff80240082fed54e3e2e0faf4 +size 836400064 diff --git a/gemma-3-1b-thinking-v2.Q6_K.gguf b/gemma-3-1b-thinking-v2.Q6_K.gguf new file mode 100644 index 0000000..af6bd2a --- /dev/null +++ b/gemma-3-1b-thinking-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f51d2f7e9655dc45287d4b39f0dea07d8eca00c2190b6d8b3346c6c6771f30d +size 1011739072 diff --git a/gemma-3-1b-thinking-v2.Q8_0.gguf b/gemma-3-1b-thinking-v2.Q8_0.gguf new file mode 100644 index 0000000..feee075 --- /dev/null +++ b/gemma-3-1b-thinking-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24255994140207bc6416ceddb4121652ddb6ccfb6d13e55ca4a21221b1061ecb +size 1069306816 diff --git a/gemma-3-1b-thinking-v2.fp16.gguf b/gemma-3-1b-thinking-v2.fp16.gguf new file mode 100644 index 0000000..f31327e --- /dev/null +++ b/gemma-3-1b-thinking-v2.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25ced546bb4a18471414b393d257eb48d30f24fc5c79144d6528866225bb716 +size 2006574016