diff --git a/gallery/index.yaml b/gallery/index.yaml index 643e2b9a4151..a1b1e8dafc03 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -5863,7 +5863,11 @@ - filename: llama-cpp/mmproj/kai-os_Grug-12B-Q8_0/mmproj-kai-os_Grug-12B-f16.gguf sha256: 0d59c7571a593b8d11c8104ed90250656efec0abbed9b4a737e7247eae149378 uri: huggingface://bartowski/kai-os_Grug-12B-GGUF/mmproj-kai-os_Grug-12B-f16.gguf -- name: "gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2" +- &gemma-4-12b-agentic-tau2 + name: "gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2" + variants: + - model: gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2-mtp + - model: gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2-q8 url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: - https://huggingface.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF @@ -5911,6 +5915,79 @@ - filename: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q4_K_M.gguf sha256: 0b9506cab36f7f818e34f9c0f5a3d6568d0b37100f3a3e1092e2eec3c4c96791 uri: https://huggingface.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/resolve/main/gemma4-v2-Q4_K_M.gguf +- !!merge <<: *gemma-4-12b-agentic-tau2 + name: "gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2-mtp" + variants: [] + description: | + Gemma 4 12B Agentic v2 is an Apache-2.0 fine-tune for coding, terminal + work, multi-step tool use, and reasoning. This variant pairs the Q4_K_M + target with the upstream Q8_0 Gemma 4 MTP drafter for faster lossless + generation through llama.cpp speculative decoding. + tags: + - llm + - gguf + - reasoning + - thinking + - mtp + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + options: + - use_jinja:true + - spec_type:draft-mtp + - spec_n_max:4 + draft_model: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma-4-12B-it-MTP-Q8_0.gguf + parameters: + min_p: 0 + model: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q4_K_M.gguf + repeat_penalty: 1 + temperature: 1 + top_k: 64 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q4_K_M.gguf + sha256: 0b9506cab36f7f818e34f9c0f5a3d6568d0b37100f3a3e1092e2eec3c4c96791 + uri: huggingface://yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q4_K_M.gguf + - filename: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma-4-12B-it-MTP-Q8_0.gguf + sha256: 145db9094bc0f85f1701e255a2ed216dcc9800fc8bc8631ad00905b456bd451b + uri: huggingface://yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/MTP/gemma-4-12B-it-MTP-Q8_0.gguf +- !!merge <<: *gemma-4-12b-agentic-tau2 + name: "gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2-q8" + variants: [] + description: | + Gemma 4 12B Agentic v2 is an Apache-2.0 fine-tune for coding, terminal + work, multi-step tool use, and reasoning. This variant uses the + near-lossless Q8_0 GGUF quantization for higher output fidelity. + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + options: + - use_jinja:true + parameters: + min_p: 0 + model: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q8_0.gguf + repeat_penalty: 1 + temperature: 1 + top_k: 64 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q8_0.gguf + sha256: 2c20a496baf3e9a3ead59d37c7afe228a863662d58155f360d44eb8b2465cb7f + uri: huggingface://yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF/gemma4-v2-Q8_0.gguf - name: "qwen3.6-27b-mtp-pi-tune" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: