diff --git a/gallery/index.yaml b/gallery/index.yaml index 764c456ad..5b73ab869 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -79941,3 +79941,87 @@ top_p: 0.95 template: use_tokenizer_template: true +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: hy-memory-30b-a3b-q4 + description: | + Tencent Hy-Memory is a 30B MoE model with about 3B active parameters + for writing and updating long-term memory in external agent frameworks. + This Q4_K_M build uses llama.cpp with the embedded chat template and + no-think mode. It supports English and Chinese; the memory framework + must supply the task prompts and persistent storage. + license: apache-2.0 + urls: + - https://huggingface.co/tencent/Hy-Memory-30B-A3B + - https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - memory + - english + - chinese + files: + - filename: Hy-Memory-30B-A3B-Q4_K_M.gguf + sha256: e417fc86d0a2bb058ed253028f4617d144aa874b8af35711cca0c7009bd63446 + uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q4_K_M.gguf + overrides: + backend: llama-cpp + chat_template_kwargs: + reasoning_effort: no_think + context_size: 8192 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: Hy-Memory-30B-A3B-Q4_K_M.gguf + repeat_penalty: 1.0 + temperature: 0.7 + top_k: 0 + top_p: 1.0 + template: + use_tokenizer_template: true + variants: + - model: hy-memory-30b-a3b-q8 +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: hy-memory-30b-a3b-q8 + description: | + Tencent Hy-Memory is a 30B MoE model with about 3B active parameters + for writing and updating long-term memory in external agent frameworks. + This Q8_0 build uses llama.cpp with the embedded chat template and + no-think mode. It supports English and Chinese; the memory framework + must supply the task prompts and persistent storage. + license: apache-2.0 + urls: + - https://huggingface.co/tencent/Hy-Memory-30B-A3B + - https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - memory + - english + - chinese + files: + - filename: Hy-Memory-30B-A3B-Q8_0.gguf + sha256: 3ba2897dbb7e21e618cb65cec4b31498e59eca2960b381c5e0a0590e7ce8526b + uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q8_0.gguf + overrides: + backend: llama-cpp + chat_template_kwargs: + reasoning_effort: no_think + context_size: 8192 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: Hy-Memory-30B-A3B-Q8_0.gguf + repeat_penalty: 1.0 + temperature: 0.7 + top_k: 0 + top_p: 1.0 + template: + use_tokenizer_template: true diff --git a/gallery/models/index.yaml b/gallery/models/index.yaml index 9410760d6..03a5d74e5 100644 --- a/gallery/models/index.yaml +++ b/gallery/models/index.yaml @@ -98170,3 +98170,103 @@ top_p: 0.95 template: use_tokenizer_template: true +- kind: model + id: hy-memory-30b-a3b-q4 + name: hy-memory-30b-a3b-q4 + version: 0.0.0-gallery.9e00023fd8c5 + description: | + Tencent Hy-Memory is a 30B MoE model with about 3B active parameters + for writing and updating long-term memory in external agent frameworks. + This Q4_K_M build uses llama.cpp with the embedded chat template and + no-think mode. It supports English and Chinese; the memory framework + must supply the task prompts and persistent storage. + license: apache-2.0 + urls: + - https://huggingface.co/tencent/Hy-Memory-30B-A3B + - https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - memory + - english + - chinese + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: Hy-Memory-30B-A3B-Q4_K_M.gguf + sha256: e417fc86d0a2bb058ed253028f4617d144aa874b8af35711cca0c7009bd63446 + uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q4_K_M.gguf + overrides: + backend: llama-cpp + chat_template_kwargs: + reasoning_effort: no_think + context_size: 8192 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: Hy-Memory-30B-A3B-Q4_K_M.gguf + repeat_penalty: 1.0 + temperature: 0.7 + top_k: 0 + top_p: 1.0 + template: + use_tokenizer_template: true + variants: + - model: hy-memory-30b-a3b-q8 +- kind: model + id: hy-memory-30b-a3b-q8 + name: hy-memory-30b-a3b-q8 + version: 0.0.0-gallery.1da8190960d9 + description: | + Tencent Hy-Memory is a 30B MoE model with about 3B active parameters + for writing and updating long-term memory in external agent frameworks. + This Q8_0 build uses llama.cpp with the embedded chat template and + no-think mode. It supports English and Chinese; the memory framework + must supply the task prompts and persistent storage. + license: apache-2.0 + urls: + - https://huggingface.co/tencent/Hy-Memory-30B-A3B + - https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - memory + - english + - chinese + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: Hy-Memory-30B-A3B-Q8_0.gguf + sha256: 3ba2897dbb7e21e618cb65cec4b31498e59eca2960b381c5e0a0590e7ce8526b + uri: https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF/resolve/38e10a37701e1caff4a6dc3831448aaf8c2e15d1/Hy-Memory-30B-A3B-Q8_0.gguf + overrides: + backend: llama-cpp + chat_template_kwargs: + reasoning_effort: no_think + context_size: 8192 + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: Hy-Memory-30B-A3B-Q8_0.gguf + repeat_penalty: 1.0 + temperature: 0.7 + top_k: 0 + top_p: 1.0 + template: + use_tokenizer_template: true