commit 78302aeaafadf97e846d921c14ebb8e4084484a6 Author: ModelHub XC Date: Sun Apr 19 03:00:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: matrixportalx/gemma-2-2b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..578dcb1 --- /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 +gemma-2-2b-it-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-2b-it-f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-2b-it-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-2b-it-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-2b-it-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-2b-it-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6f641d0 --- /dev/null +++ b/README.md @@ -0,0 +1,59 @@ +--- +license: gemma +library_name: transformers +pipeline_tag: text-generation +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +extra_gated_button_content: Acknowledge license +tags: +- conversational +- llama-cpp +- gguf-my-repo +base_model: google/gemma-2-2b-it +--- + +# matrixportal/gemma-2-2b-it-GGUF +This model was converted to GGUF format from [`google/gemma-2-2b-it`](https://huggingface.co/google/gemma-2-2b-it) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. +Refer to the [original model card](https://huggingface.co/google/gemma-2-2b-it) for more details on the model. + +## Use with llama.cpp +Install llama.cpp through brew (works on Mac and Linux) + +```bash +brew install llama.cpp + +``` +Invoke the llama.cpp server or the CLI. + +### CLI: +```bash +llama-cli --hf-repo matrixportal/gemma-2-2b-it-GGUF --hf-file gemma-2-2b-it-q5_k_m.gguf -p "The meaning to life and the universe is" +``` + +### Server: +```bash +llama-server --hf-repo matrixportal/gemma-2-2b-it-GGUF --hf-file gemma-2-2b-it-q5_k_m.gguf -c 2048 +``` + +Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. + +Step 1: Clone llama.cpp from GitHub. +``` +git clone https://github.com/ggerganov/llama.cpp +``` + +Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). +``` +cd llama.cpp && LLAMA_CURL=1 make +``` + +Step 3: Run inference through the main binary. +``` +./llama-cli --hf-repo matrixportal/gemma-2-2b-it-GGUF --hf-file gemma-2-2b-it-q5_k_m.gguf -p "The meaning to life and the universe is" +``` +or +``` +./llama-server --hf-repo matrixportal/gemma-2-2b-it-GGUF --hf-file gemma-2-2b-it-q5_k_m.gguf -c 2048 +``` diff --git a/gemma-2-2b-it-f16.gguf b/gemma-2-2b-it-f16.gguf new file mode 100644 index 0000000..314b298 --- /dev/null +++ b/gemma-2-2b-it-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3020c905bffdc3e48d3e403177ba0546d72b5e5e93322d0eb8150e166d92e5a +size 5235214176 diff --git a/gemma-2-2b-it-q4_k_m.gguf b/gemma-2-2b-it-q4_k_m.gguf new file mode 100644 index 0000000..d8801cb --- /dev/null +++ b/gemma-2-2b-it-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9de40ca88a0f9a0c229d8ee97f9db1a4f533ef5d9aa955cb6cfba814fb96b29 +size 1708582752 diff --git a/gemma-2-2b-it-q5_k_m.gguf b/gemma-2-2b-it-q5_k_m.gguf new file mode 100644 index 0000000..160221d --- /dev/null +++ b/gemma-2-2b-it-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b514d24747a725660e84ed7778dc0a374fd1155659cd8e1064e57882d57d786 +size 1923278688 diff --git a/gemma-2-2b-it-q5_k_s.gguf b/gemma-2-2b-it-q5_k_s.gguf new file mode 100644 index 0000000..ce35cb3 --- /dev/null +++ b/gemma-2-2b-it-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50f490839ae38697165464e6b459966ac70d66c62160cb5778ac5c70357e58b +size 1882543968 diff --git a/gemma-2-2b-it-q6_k.gguf b/gemma-2-2b-it-q6_k.gguf new file mode 100644 index 0000000..3ae577c --- /dev/null +++ b/gemma-2-2b-it-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a32524a1eec1931ebafb5ed24f19dcc2561b1c86d3fa02a578fca4bd34def1c +size 2151393120 diff --git a/gemma-2-2b-it-q8_0.gguf b/gemma-2-2b-it-q8_0.gguf new file mode 100644 index 0000000..1bd469b --- /dev/null +++ b/gemma-2-2b-it-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d69e1c933f8297fc3e5d915ac964cb37f9b19ffa42392c81bdfaa37d770d6ee +size 2784495456