commit 073415faaf980ea46634c42b8d2531be639d48e6 Author: ModelHub XC Date: Mon Sep 7 12:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: sayhan/gemma-7b-GGUF-quantized Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6bddeb8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +gemma-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-fp16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q2_K-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q3_K_L-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q3_K_M-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q3_K_S-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q4_0-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q4_K_M-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q4_K_S-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q5_0-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q5_K_M-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q5_K_S-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q6_K-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b.Q8_0-v2.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e2bcab7 --- /dev/null +++ b/README.md @@ -0,0 +1,53 @@ +--- +base_model: google/gemma-7b +language: +- en +pipeline_tag: text-generation +license: other +model_type: gemma +library_name: transformers +inference: false +--- +![image/webp](https://cdn-uploads.huggingface.co/production/uploads/65aa2d4b356bf23b4a4da247/NQAvp6NRHlNILyWWFlrA7.webp) +## Google Gemma 7B +- **Model creator:** [Google](https://huggingface.co/google) +- **Original model:** [gemma-7b-it](https://huggingface.co/google/gemma-7b) +- [**Terms of use**](https://www.kaggle.com/models/google/gemma/license/consent) + +## Description +This repo contains GGUF format model files for [Google's Gemma 7B](https://huggingface.co/google/gemma-7b) + +## Original model +- **Developed by:** [Google](https://huggingface.co/google) + +### Description +Gemma is a family of lightweight, state-of-the-art open models from Google, +built from the same research and technology used to create the Gemini models. +They are text-to-text, decoder-only large language models, available in English, +with open weights, pre-trained variants, and instruction-tuned variants. Gemma +models are well-suited for a variety of text generation tasks, including +question answering, summarization, and reasoning. Their relatively small size +makes it possible to deploy them in environments with limited resources such as +a laptop, desktop or your own cloud infrastructure, democratizing access to +state of the art AI models and helping foster innovation for everyone. + +## Quantizon types +| quantization method | bits | size | description | recommended | +|---------------------|------|----------|-----------------------------------------------------|-------------| +| Q2_K | 2 | 3.09 | very small, very high quality loss | ❌ | +| Q3_K_S | 3 | 3.68 GB | very small, high quality loss | ❌ | +| Q3_K_L | 3 | 4.4 GB | small, substantial quality loss | ❌ | +| Q4_0 | 4 | 4.81 GB | legacy; small, very high quality loss | ❌ | +| Q4_K_S | 4 | 4.84 GB | medium, balanced quality | ✅ | +| Q4_K_M | 4 | 5.13 GB | medium, balanced quality | ✅ | +| Q5_0 | 5 | 5.88 GB | legacy; medium, balanced quality | ❌ | +| Q5_K_S | 5 | 5.88 GB | large, low quality loss | ✅ | +| Q5_K_M | 5 | 6.04 GB | large, very low quality loss | ✅ | +| Q6_K | 6 | 7.01 GB | very large, extremely low quality loss | ❌ | +| Q8_0 | 8 | 9.08 GB | very large, extremely low quality loss | ❌ | +| FP16 | 16 | 17.1 GB | enormous, negligible quality loss | ❌ | + +## Usage +You can use this model with the latest builds of **LM Studio** and **llama.cpp**. +If you're new to the world of _large language models_, I recommend starting with **LM Studio**. + \ No newline at end of file diff --git a/gemma-7b-fp16.gguf b/gemma-7b-fp16.gguf new file mode 100644 index 0000000..2ab0cf1 --- /dev/null +++ b/gemma-7b-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df20ea2eb82cba9e4106ac6ee87629776cd60a07a02e0d04a7d0666c4ed0248 +size 17081755936 diff --git a/gemma-7b.Q2_K-v2.gguf b/gemma-7b.Q2_K-v2.gguf new file mode 100644 index 0000000..ddee9ef --- /dev/null +++ b/gemma-7b.Q2_K-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad369df9cc5ac513b260d091bcbc43c004e7ba84a2c5c15604e5fbb7036c95e +size 3094374752 diff --git a/gemma-7b.Q3_K_L-v2.gguf b/gemma-7b.Q3_K_L-v2.gguf new file mode 100644 index 0000000..b167de9 --- /dev/null +++ b/gemma-7b.Q3_K_L-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc341b435a127925a251cdd9c0f3f2f6d9ee2c3f35aa62dfe63b2121bd1e13ba +size 4401867104 diff --git a/gemma-7b.Q3_K_M-v2.gguf b/gemma-7b.Q3_K_M-v2.gguf new file mode 100644 index 0000000..e58e54c --- /dev/null +++ b/gemma-7b.Q3_K_M-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669e9d0c9bfd41417516a52dc684cec301891a6da2a1486b2e8eb6a96c134e09 +size 4062128480 diff --git a/gemma-7b.Q3_K_S-v2.gguf b/gemma-7b.Q3_K_S-v2.gguf new file mode 100644 index 0000000..a3712f6 --- /dev/null +++ b/gemma-7b.Q3_K_S-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a035d19a7f6cc1e0a6a05095761e467fd1c445afdf80cb039c05628b8c7f917a +size 3675203936 diff --git a/gemma-7b.Q4_0-v2.gguf b/gemma-7b.Q4_0-v2.gguf new file mode 100644 index 0000000..a80bde8 --- /dev/null +++ b/gemma-7b.Q4_0-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58bbbe5a407f7cac3044e1c3a209e8ee4eb8e920d253bc47dc6853f4563a1a8 +size 4809091424 diff --git a/gemma-7b.Q4_K_M-v2.gguf b/gemma-7b.Q4_K_M-v2.gguf new file mode 100644 index 0000000..c621568 --- /dev/null +++ b/gemma-7b.Q4_K_M-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d523fc678f0a8640cb306ca6d706ce7b58e1e331d6a9295e9e3577546df656f +size 5127006560 diff --git a/gemma-7b.Q4_K_S-v2.gguf b/gemma-7b.Q4_K_S-v2.gguf new file mode 100644 index 0000000..48f325f --- /dev/null +++ b/gemma-7b.Q4_K_S-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de353d1e4945395f0465b95c28c3acf34e09d4cf6fdcd95ffe4b4b88cc373dd8 +size 4843694432 diff --git a/gemma-7b.Q5_0-v2.gguf b/gemma-7b.Q5_0-v2.gguf new file mode 100644 index 0000000..0789f22 --- /dev/null +++ b/gemma-7b.Q5_0-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1509b000053b4fe017a9d722bec891fb1c1ff4ec1031d87357181c298e5700e0 +size 5876279648 diff --git a/gemma-7b.Q5_K_M-v2.gguf b/gemma-7b.Q5_K_M-v2.gguf new file mode 100644 index 0000000..35d4964 --- /dev/null +++ b/gemma-7b.Q5_K_M-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4454d137becf10728b6e94c5da5a43b2b4d7e49d01c9343d1de26e179eab6d16 +size 6040054112 diff --git a/gemma-7b.Q5_K_S-v2.gguf b/gemma-7b.Q5_K_S-v2.gguf new file mode 100644 index 0000000..5a1cdd6 --- /dev/null +++ b/gemma-7b.Q5_K_S-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e43f3a6139f2f0ab867b45a1f72fd024b9cdc7fe2da2e41847e2e1d434d4397 +size 5876279648 diff --git a/gemma-7b.Q6_K-v2.gguf b/gemma-7b.Q6_K-v2.gguf new file mode 100644 index 0000000..3157b28 --- /dev/null +++ b/gemma-7b.Q6_K-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0765e6a8845ca467f559f139a6ac8a817e53e64b0834df847c3b3ea803edfb0 +size 7010167136 diff --git a/gemma-7b.Q8_0-v2.gguf b/gemma-7b.Q8_0-v2.gguf new file mode 100644 index 0000000..9192d07 --- /dev/null +++ b/gemma-7b.Q8_0-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a945698cac9f296a9d638ecbd0935387477fd0ad682b4be19e372036ea6e8c7 +size 9077844320