diff --git a/gallery/index.yaml b/gallery/index.yaml index ac825cdae028..ef01e65d625a 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,4 +1,90 @@ --- +- name: "huihui-glm-5.2-abliterated" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF + description: | + # GLM-5.2 + + 👋 Join our WeChat or Discord community. + + 📖 Check out the GLM-5.2 blog and GLM-5 Technical report. + + 📍 Use GLM-5.2 API services on Z.ai API Platform. + + 🔜 Try GLM-5.2 here. + + [Paper] + [GitHub] + + ## Introduction + + We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**. GLM-5.2's new capabilities include: + - **Solid 1M Context:** A solid 1M-token context that stably sustains long-horizon work + - **Advanced Coding with Flexible Effort**: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency + - **Improved Architecture**: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20% + - **Pure Open**: An MIT open-source license — no regional limits, technical access without borders + + ## Benchmark + + ## Serve GLM-5.2 Locally + + ... + license: "mit" + tags: + - llm + - gguf + icon: https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_52.png + 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:6 + - spec_p_min:0.75 + parameters: + min_p: 0.01 + model: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00001-of-00009.gguf + repeat_penalty: 1 + temperature: 1 + top_k: -1 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00001-of-00009.gguf + sha256: f3d949f4dd553f0c3df4e0f4c7e159d026543e003917fe2bbcb1fac7cd193ab7 + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00001-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00002-of-00009.gguf + sha256: 2c40fcc394d7efabdef09035bf604f89fcd8350c4a45ced60a1eab54c7ebe1bf + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00002-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00003-of-00009.gguf + sha256: 66420296e334730183f0bb6a6b9eca09b180b4409f5ebe67efc71f41517b311e + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00003-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00004-of-00009.gguf + sha256: 08da8ecf994bb7308a01dd891d4947604131c3e13858b4421f2374b0a282e616 + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00004-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00005-of-00009.gguf + sha256: 2c5ee855e12f1b8ddbaebb81269d84ea37c46b1ff73f2cdf205cba835f7c03af + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00005-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00006-of-00009.gguf + sha256: 7048ab8b9f8314f11ef13046ea5bc14438fc38b2509066a05e3ed0a6cad61eee + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00006-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00007-of-00009.gguf + sha256: a2a855a9fa12161e92ab9eddaa225ae5930073ef59a447ac08ea76b2d3761b7a + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00007-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00008-of-00009.gguf + sha256: 3bad6d7b480999f7271ad5361c6b1a3e210f25698ff8cb7e1f8c4e435241d12b + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00008-of-00009.gguf + - filename: llama-cpp/models/GLM-5.2-UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00009-of-00009.gguf + sha256: 22eef33ffce83e24f5c1d008a63cb45ae2510f26c08d115bf2f7880688fd3c7a + uri: https://huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF/resolve/main/UD-Q3_K_M/GLM-5.2-UD-Q3_K_M-00009-of-00009.gguf - name: "qwen-agentworld-35b-a3b" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: