diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index 58aa920f9..95577b9b1 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -39,6 +39,14 @@ Both views use the same model selection and store the view, search, filter, and selection in the URL. Installing from Explore does not move you away from the catalog; the entry updates in place when the operation finishes. +## Cyber-Tiel-Coder + +Install `cyber-tiel-coder-35b-a3b-q4-mtp` for coding and image chat with llama.cpp. +The gallery groups UD-Q4_K_XL and UD-Q8_K_XL builds; both enable MTP speculative decoding and include a BF16 vision projector. +To select Q8 explicitly, run `local-ai models install cyber-tiel-coder-35b-a3b-q4-mtp --variant cyber-tiel-coder-35b-a3b-q8-mtp`. +Both configurations use the embedded chat template and default to 32,768 context tokens. +The [model card](https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP) describes its abliterated Ornith-1.5 base and MIT license. + ## MiMo-V2.6-Distill-Qwen-9B Install `mimo-v2.6-distill-qwen-9b` for text and image chat with llama.cpp. diff --git a/gallery/index.yaml b/gallery/index.yaml index 60de2ff8e..7cf86f58a 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -4767,6 +4767,110 @@ - filename: llama-cpp/mmproj/thomson-1.0-small/mmproj-bf16.gguf uri: huggingface://bartowski/thomsonreuters_Thomson-1.0-Small-GGUF/mmproj-thomsonreuters_Thomson-1.0-Small-bf16.gguf sha256: 11634fcccd59c23f1b95e34e5cf479dec86290eeb3dda980324aabd8b0b48f41 +- name: cyber-tiel-coder-35b-a3b-q4-mtp + variants: + - model: cyber-tiel-coder-35b-a3b-q8-mtp + url: github:mudler/LocalAI/gallery/virtual.yaml@master + license: mit + urls: + - https://huggingface.co/huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated + - https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Cyber-Tiel-Coder is a 35B mixture-of-experts coding model with 3B active parameters, + based on Huihui's abliterated Ornith-1.5. This UD-Q4_K_XL build includes + MTP speculative decoding, the embedded Sharp chat template, and a BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - coding + - tools + - vision + - multimodal + - mtp + overrides: + backend: llama-cpp + context_size: 32768 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/cyber-tiel-coder-35b-a3b/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/cyber-tiel-coder-35b-a3b/Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL.gguf + temperature: 0.6 + top_p: 0.95 + top_k: 20 + min_p: 0.0 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/cyber-tiel-coder-35b-a3b/Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/resolve/fa19d4f33561dc0d107c2a2f8943f1ca2e288109/Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q4_K_XL.gguf + sha256: 0bbcf3cc9be4c976bad20e641baf629dad9c178d39ebdc9cd72129179943c06a + - filename: llama-cpp/mmproj/cyber-tiel-coder-35b-a3b/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/resolve/fa19d4f33561dc0d107c2a2f8943f1ca2e288109/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- name: cyber-tiel-coder-35b-a3b-q8-mtp + url: github:mudler/LocalAI/gallery/virtual.yaml@master + license: mit + urls: + - https://huggingface.co/huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated + - https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Cyber-Tiel-Coder is a 35B mixture-of-experts coding model with 3B active parameters, + based on Huihui's abliterated Ornith-1.5. This UD-Q8_K_XL build includes + MTP speculative decoding, the embedded Sharp chat template, and a BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - coding + - tools + - vision + - multimodal + - mtp + overrides: + backend: llama-cpp + context_size: 32768 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/cyber-tiel-coder-35b-a3b/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/cyber-tiel-coder-35b-a3b/Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + temperature: 0.6 + top_p: 0.95 + top_k: 20 + min_p: 0.0 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/cyber-tiel-coder-35b-a3b/Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/resolve/fa19d4f33561dc0d107c2a2f8943f1ca2e288109/Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + sha256: 601052bb18c97b40808a5d93992b25eeb64b9b0bc5e2de0681c15681adf19961 + - filename: llama-cpp/mmproj/cyber-tiel-coder-35b-a3b/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/resolve/fa19d4f33561dc0d107c2a2f8943f1ca2e288109/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 - &tiel-coder-35b-a3b name: "tiel-coder-35b-a3b-q4" variants: