diff --git a/gallery/index.yaml b/gallery/index.yaml index 571587635..548ad2f2d 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,5 +1,50 @@ --- -- name: "deepseek-v4-flash-vision-exp" +- name: "minicpm5-2b" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/openbmb/MiniCPM5-2B-GGUF + description: | + MiniCPM Tech Report | + MiniCPM Wiki(Chinese) | + GitHub Repo | + UltraData | + Online Demo + + English | + δΈ­ζ–‡ + + ## Highlights + + We are releasing **MiniCPM5-2B**, the second model in the **MiniCPM5** series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA. + + πŸ† **2B-class open-source SOTA**: compared with strong open-source models of similar size, MiniCPM5-2B achieves SOTA performance within this comparison set. It remains competitive with 4B-class models overall, while showing its advantages over models of comparable size in coding, mathematics, long-context understanding, tool use, and agentic tasks. + + ... + license: "apache-2.0" + tags: + - llm + - gguf + - llama + icon: https://raw.githubusercontent.com/OpenBMB/MiniCPM/main/assets/minicpm5/minicpm5_2b_training_recipe.jpg + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + options: + - use_jinja:true + parameters: + model: llama-cpp/models/MiniCPM5-2B-Q4_K_M/MiniCPM5-2B-Q4_K_M.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/MiniCPM5-2B-Q4_K_M/MiniCPM5-2B-Q4_K_M.gguf + sha256: ec2d5801640099e97d8d7e8003ad4d81f336e757811f03a26173dddf386602fd + uri: https://huggingface.co/openbmb/MiniCPM5-2B-GGUF/resolve/main/MiniCPM5-2B-Q4_K_M.gguf +- name: "qwopus3.8-27b-flash" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: - https://huggingface.co/unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF