commit 53257c5052e53905f47d317d634c92a7f2511112 Author: ModelHub XC Date: Thu Jul 16 16:56:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: sayhan/gemma-7b-it-GGUF-quantized Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8bfff8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it-fp16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_L-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_M-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_S-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_0-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_K_M-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_K_S-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_0-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_K_M-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_K_S-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q6_K-v2.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.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..bfe2b5a --- /dev/null +++ b/README.md @@ -0,0 +1,51 @@ +--- +base_model: google/gemma-7b-it +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 Instruct +- **Model creator:** [Google](https://huggingface.co/google) +- **Original model:** [gemma-7b-it](https://huggingface.co/google/gemma-7b-it) +- [**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 Instruct](https://huggingface.co/google/gemma-7b-it) + +## 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 | +|---------------------|------|----------|-----------------------------------------------------|-------------| +| 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_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-it-fp16.gguf b/gemma-7b-it-fp16.gguf new file mode 100644 index 0000000..660033b --- /dev/null +++ b/gemma-7b-it-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19e52732bddcb9902347a9c60c117801ad7a3b776b700b9d1649f63f6d80dc0 +size 17081756544 diff --git a/gemma-7b-it.Q3_K_L-v2.gguf b/gemma-7b-it.Q3_K_L-v2.gguf new file mode 100644 index 0000000..827dd08 --- /dev/null +++ b/gemma-7b-it.Q3_K_L-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9faa5a960635f5967b70b7f316266f7ddccdd2a71496c0c11c4fbf751ad3bec4 +size 4401867744 diff --git a/gemma-7b-it.Q3_K_M-v2.gguf b/gemma-7b-it.Q3_K_M-v2.gguf new file mode 100644 index 0000000..a3f2fc0 --- /dev/null +++ b/gemma-7b-it.Q3_K_M-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a30107cc0408bc9e89fba817929979aed868730f07dc063bcfcd8a273d6a3a7 +size 4062129120 diff --git a/gemma-7b-it.Q3_K_S-v2.gguf b/gemma-7b-it.Q3_K_S-v2.gguf new file mode 100644 index 0000000..f072c4e --- /dev/null +++ b/gemma-7b-it.Q3_K_S-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de33322c8827fcf52c272355eb37208353f37011fa309744ceec05dce8e44e4 +size 3675204576 diff --git a/gemma-7b-it.Q4_0-v2.gguf b/gemma-7b-it.Q4_0-v2.gguf new file mode 100644 index 0000000..035f539 --- /dev/null +++ b/gemma-7b-it.Q4_0-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec234811467d551dc51c398d97ba6d4d6dce55eac210483e940e6e57c97309e2 +size 4809092064 diff --git a/gemma-7b-it.Q4_K_M-v2.gguf b/gemma-7b-it.Q4_K_M-v2.gguf new file mode 100644 index 0000000..789a38c --- /dev/null +++ b/gemma-7b-it.Q4_K_M-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457449b3e6f41a6d7d774c06a59e518ae9bb329225c415eea47bca414b2e9643 +size 5127007200 diff --git a/gemma-7b-it.Q4_K_S-v2.gguf b/gemma-7b-it.Q4_K_S-v2.gguf new file mode 100644 index 0000000..21c7373 --- /dev/null +++ b/gemma-7b-it.Q4_K_S-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624c5a35bb7e297336e5e2c0868566065b5ce4002c4378a7832790dc2d2ceef5 +size 4843695072 diff --git a/gemma-7b-it.Q5_0-v2.gguf b/gemma-7b-it.Q5_0-v2.gguf new file mode 100644 index 0000000..4344c22 --- /dev/null +++ b/gemma-7b-it.Q5_0-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f12cc04ef24077de544af7db3371b9d4c463aec8bb94a44f36564b6745687f0 +size 5876280288 diff --git a/gemma-7b-it.Q5_K_M-v2.gguf b/gemma-7b-it.Q5_K_M-v2.gguf new file mode 100644 index 0000000..d67f9c4 --- /dev/null +++ b/gemma-7b-it.Q5_K_M-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528611c83f8a40c3009863ae787c2e21d7db9320c96b708702166280730ce971 +size 6040054752 diff --git a/gemma-7b-it.Q5_K_S-v2.gguf b/gemma-7b-it.Q5_K_S-v2.gguf new file mode 100644 index 0000000..5ed70df --- /dev/null +++ b/gemma-7b-it.Q5_K_S-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29acd8103ba6d88b7846a99796fe59eaeeb39b95640e4268e462ac6e434e8f5e +size 5876280288 diff --git a/gemma-7b-it.Q6_K-v2.gguf b/gemma-7b-it.Q6_K-v2.gguf new file mode 100644 index 0000000..0e95b9f --- /dev/null +++ b/gemma-7b-it.Q6_K-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cbd27f2332c09a265eb3509f05672656827556f98489f902cf941e9b920ce7 +size 7010167776 diff --git a/gemma-7b-it.Q8_0-v2.gguf b/gemma-7b-it.Q8_0-v2.gguf new file mode 100644 index 0000000..cc0ca8d --- /dev/null +++ b/gemma-7b-it.Q8_0-v2.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f092aa54e2472e66085030edd77d038df72ceaefae7bbf7de1ff3262eb6625 +size 9077844960