From c7ff1aabf07ea9b987404bd7c4eb28c61c8dd827 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 11 Sep 2026 22:37:33 +0000 Subject: [PATCH] gallery: apply PR #11947 Assisted-by: localai-org-maint-bot:glm5.2 [gh] --- docs/content/features/model-gallery.md | 14 +-- gallery/index.yaml | 156 +++++++++++++++++++++++++ 2 files changed, 159 insertions(+), 11 deletions(-) diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index 30ad2d17f..b4ed06d1c 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -298,19 +298,11 @@ whole page has variants. curl http://localhost:8080/api/models | jq '.models[] | select(.has_variants) | .name' ``` -### MiniCPM5-2B - -[MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B) is available as -`minicpm5-2b` (Q4_K_M) and `minicpm5-2b-q8` (Q8_0) for the llama.cpp -backend. The Q4 entry offers Q8 as a variant, so LocalAI can select a build -that fits the host. Both use the model's embedded chat template, an 8,192-token -context, temperature 1.0, and top-p 0.95. These entries support text chat; -OpenAI-compatible tool calling has not been verified. - -To select the Q4 build explicitly: +The Tiel-Coder gallery entry offers Q4, Q5, Q6, and Q8 MTP builds for +llama.cpp, each with the BF16 vision projector. To select the Q6 MTP build: ```bash -local-ai models install minicpm5-2b --variant minicpm5-2b +local-ai models install tiel-coder-35b-a3b-q4 --variant tiel-coder-35b-a3b-q6-mtp ``` ### Collapsing the listing to one row per model diff --git a/gallery/index.yaml b/gallery/index.yaml index e399c8d6a..e8fb95a64 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3345,6 +3345,9 @@ name: "tiel-coder-35b-a3b-q4" variants: - model: tiel-coder-35b-a3b-q4-mtp + - model: tiel-coder-35b-a3b-q5-mtp + - model: tiel-coder-35b-a3b-q6-mtp + - model: tiel-coder-35b-a3b-q8-mtp - model: tiel-coder-35b-a3b-q8 url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: @@ -3445,6 +3448,159 @@ - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf uri: huggingface://peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/mmproj-BF16.gguf sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- !!merge <<: *tiel-coder-35b-a3b + name: "tiel-coder-35b-a3b-q5-mtp" + variants: [] + last_checked: "2026-09-09" + urls: + - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B + - https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Tiel-Coder-35B-A3B in Q5_K_XL format with MTP speculative decoding and a + BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - reasoning + - thinking + - coding + - agent + - tools + - vision + - multimodal + - long-context + - mtp + overrides: + backend: llama-cpp + context_size: 262144 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf + sha256: 83278fd1ea9923edb45cf6d373a8aa6475fb1f855795e085b9e6252bc53f24fa + - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- !!merge <<: *tiel-coder-35b-a3b + name: "tiel-coder-35b-a3b-q6-mtp" + variants: [] + last_checked: "2026-09-09" + urls: + - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B + - https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Tiel-Coder-35B-A3B in Q6_K_XL format with MTP speculative decoding and a + BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - reasoning + - thinking + - coding + - agent + - tools + - vision + - multimodal + - long-context + - mtp + overrides: + backend: llama-cpp + context_size: 262144 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf + sha256: a13a71ecfd00779fa3e0071674da61afbdffd42050f22173f4142989975573ba + - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- !!merge <<: *tiel-coder-35b-a3b + name: "tiel-coder-35b-a3b-q8-mtp" + variants: [] + last_checked: "2026-09-09" + urls: + - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B + - https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Tiel-Coder-35B-A3B in Q8_K_XL format with MTP speculative decoding and a + BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - reasoning + - thinking + - coding + - agent + - tools + - vision + - multimodal + - long-context + - mtp + overrides: + backend: llama-cpp + context_size: 262144 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + sha256: 8384abe448e6159b1d43249be9c51f68fe5771e962bb39e3ee89ad1215385310 + - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 - !!merge <<: *tiel-coder-35b-a3b name: "tiel-coder-35b-a3b-q8" variants: []