diff --git a/gallery/index.yaml b/gallery/index.yaml index 6691d2e51..d15eaefac 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -928,6 +928,235 @@ - filename: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V6-Q8_0/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf sha256: c8e702344a81f8c226a914aa980ed6e1f604bce9374f1fed8e65c896908af414 uri: https://huggingface.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-GGUF/resolve/main/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf +- &qwen3-6-35b-a3b-genesis-hermes-v7 + name: "qwen3.6-35b-a3b-genesis-hermes-v7" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + variants: + - model: qwen3.6-35b-a3b-genesis-hermes-v7-apex-compact + - model: qwen3.6-35b-a3b-genesis-hermes-v7-mtp-apex + - model: qwen3.6-35b-a3b-genesis-hermes-v7-mtp-apex-compact + - model: qwen3.6-35b-a3b-genesis-hermes-v7-q8-k-p + urls: + - https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive + - https://huggingface.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF + description: | + Qwen3.6-35B-A3B Genesis Hermes V7 is LuffyTheFox's Apache-2.0 multimodal, + agentic derivative of HauhauCS's uncensored Qwen3.6-35B-A3B model. It + combines Genesis tensor calibration with Hermes function-calling data while + retaining the 35B mixture-of-experts architecture, roughly 3B active + parameters per token, and the native 262K-token context window. + + This entry's own payload uses the model card's recommended APEX GGUF and the + shared F16 multimodal projector. Automatic variant selection may instead + choose Compact APEX, an MTP-enabled APEX build, or Q8_K_P based on serving + features and available memory. The model card recommends Jinja chat + templates and at least a 128K context for its thinking behavior. + license: "apache-2.0" + tags: + - llm + - gguf + - vision + - multimodal + - reasoning + - coding + - uncensored + - moe + last_checked: "2026-08-10" + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + options: + - use_jinja:true + parameters: + min_p: 0 + model: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX.gguf + repeat_penalty: 1 + temperature: 0.6 + top_k: 20 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX.gguf + sha256: 995c2a82e1aaca7947075891ead093e38d1e7dc5c0b54e4debd1d01058229ff9 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX.gguf + - filename: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + sha256: c8e702344a81f8c226a914aa980ed6e1f604bce9374f1fed8e65c896908af414 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf +- !!merge <<: *qwen3-6-35b-a3b-genesis-hermes-v7 + name: "qwen3.6-35b-a3b-genesis-hermes-v7-apex-compact" + variants: [] + description: | + Qwen3.6-35B-A3B Genesis Hermes V7 in the smaller APEX Compact GGUF format, + with the shared F16 multimodal projector. This build preserves the model's + multimodal, reasoning, coding, and agentic capabilities for hosts with less + memory than the recommended full APEX build. + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + options: + - use_jinja:true + parameters: + min_p: 0 + model: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact.gguf + repeat_penalty: 1 + temperature: 0.6 + top_k: 20 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact.gguf + sha256: 41826ae69333ab4f3577d53c0a8b427b306c63c88c6200b4eada32dda28d26b9 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-APEX-Compact.gguf + - filename: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + sha256: c8e702344a81f8c226a914aa980ed6e1f604bce9374f1fed8e65c896908af414 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf +- !!merge <<: *qwen3-6-35b-a3b-genesis-hermes-v7 + name: "qwen3.6-35b-a3b-genesis-hermes-v7-mtp-apex" + variants: [] + description: | + Qwen3.6-35B-A3B Genesis Hermes V7 in the full APEX GGUF format with native + multi-token prediction enabled for speculative decoding, plus the shared + F16 multimodal projector. + tags: + - llm + - gguf + - vision + - multimodal + - reasoning + - coding + - uncensored + - moe + - mtp + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + - spec_n_max:6 + - spec_p_min:0.75 + parameters: + min_p: 0 + model: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX.gguf + repeat_penalty: 1 + temperature: 0.6 + top_k: 20 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX.gguf + sha256: 63a3cd730a4f1e7f5b909c89550de32e5a27b33c697c62aed9da60a7bd4643ae + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX.gguf + - filename: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + sha256: c8e702344a81f8c226a914aa980ed6e1f604bce9374f1fed8e65c896908af414 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf +- !!merge <<: *qwen3-6-35b-a3b-genesis-hermes-v7 + name: "qwen3.6-35b-a3b-genesis-hermes-v7-mtp-apex-compact" + variants: [] + description: | + Qwen3.6-35B-A3B Genesis Hermes V7 in the smaller APEX Compact GGUF format + with native multi-token prediction enabled for speculative decoding, plus + the shared F16 multimodal projector. + tags: + - llm + - gguf + - vision + - multimodal + - reasoning + - coding + - uncensored + - moe + - mtp + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + - spec_n_max:6 + - spec_p_min:0.75 + parameters: + min_p: 0 + model: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact.gguf + repeat_penalty: 1 + temperature: 0.6 + top_k: 20 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact.gguf + sha256: 11edd0da4f28f587c0eb72ae2e417dfb0d02733360303045e21c9ba3aae8d114 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-MTP-APEX-Compact.gguf + - filename: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + sha256: c8e702344a81f8c226a914aa980ed6e1f604bce9374f1fed8e65c896908af414 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf +- !!merge <<: *qwen3-6-35b-a3b-genesis-hermes-v7 + name: "qwen3.6-35b-a3b-genesis-hermes-v7-q8-k-p" + variants: [] + description: | + Qwen3.6-35B-A3B Genesis Hermes V7 in the high-quality Q8_K_P GGUF format, + with the shared F16 multimodal projector. This is the largest non-MTP build + in the published V7 set. + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + options: + - use_jinja:true + parameters: + min_p: 0 + model: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P.gguf + repeat_penalty: 1 + temperature: 0.6 + top_k: 20 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P.gguf + sha256: b37a4225ba1eebaaac35b69dfeb78d1955d06fcb9f41fd334a4837cbdaff21c1 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/Hermes3.6-35B-A3B-Uncensored-Genesis-V7-Q8_K_P.gguf + - filename: llama-cpp/mmproj/Hermes3.6-35B-A3B-Uncensored-Genesis-V7/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf + sha256: c8e702344a81f8c226a914aa980ed6e1f604bce9374f1fed8e65c896908af414 + uri: huggingface://LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF/mmproj-Hermes3.6-35B-A3B-Uncensored-Genesis-F16.gguf - &kat-coder-v2-5-dev name: "kat-coder-v2.5-dev" variants: