From 27a39975309e111007a507cb247e0ba2fffeccde Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Wed, 19 Mar 2025 09:18:40 +0100 Subject: [PATCH] chore(model-gallery): :arrow_up: update checksum (#5036) :arrow_up: Checksum updates in gallery/index.yaml Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- gallery/index.yaml | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/gallery/index.yaml b/gallery/index.yaml index af36d1cd..3a03903c 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -143,24 +143,24 @@ - https://huggingface.co/soob3123/amoral-gemma3-12B - https://huggingface.co/bartowski/soob3123_amoral-gemma3-12B-GGUF description: | - A fine-tuned version of Google's Gemma 3 12B instruction-tuned model optimized for creative freedom and reduced content restrictions. This variant maintains strong reasoning capabilities while excelling in roleplaying scenarios and open-ended content generation. + A fine-tuned version of Google's Gemma 3 12B instruction-tuned model optimized for creative freedom and reduced content restrictions. This variant maintains strong reasoning capabilities while excelling in roleplaying scenarios and open-ended content generation. - Key Modifications: + Key Modifications: - Reduced refusal mechanisms compared to base model - Enhanced character consistency in dialogues - Improved narrative flow control - Optimized for multi-turn interactions + Reduced refusal mechanisms compared to base model + Enhanced character consistency in dialogues + Improved narrative flow control + Optimized for multi-turn interactions - Intended Use + Intended Use - Primary Applications: + Primary Applications: - Interactive fiction and storytelling - Character-driven roleplaying scenarios - Creative writing assistance - Experimental AI interactions - Content generation for mature audiences + Interactive fiction and storytelling + Character-driven roleplaying scenarios + Creative writing assistance + Experimental AI interactions + Content generation for mature audiences overrides: parameters: model: soob3123_amoral-gemma3-12B-Q4_K_M.gguf @@ -469,7 +469,7 @@ - https://huggingface.co/suayptalha/Maestro-10B - https://huggingface.co/bartowski/suayptalha_Maestro-10B-GGUF description: | - Maestro-10B is a 10 billion parameter model fine-tuned from Virtuoso-Lite, a next-generation language model developed by arcee-ai. Virtuoso-Lite itself is based on the Llama-3 architecture, distilled from Deepseek-v3 using approximately 1.1 billion tokens/logits. This distillation process allows Virtuoso-Lite to achieve robust performance with a smaller parameter count, excelling in reasoning, code generation, and mathematical problem-solving. Maestro-10B inherits these strengths from its base model, Virtuoso-Lite, and further enhances them through fine-tuning on the OpenOrca dataset. This combination of a distilled base model and targeted fine-tuning makes Maestro-10B a powerful and efficient language model. + Maestro-10B is a 10 billion parameter model fine-tuned from Virtuoso-Lite, a next-generation language model developed by arcee-ai. Virtuoso-Lite itself is based on the Llama-3 architecture, distilled from Deepseek-v3 using approximately 1.1 billion tokens/logits. This distillation process allows Virtuoso-Lite to achieve robust performance with a smaller parameter count, excelling in reasoning, code generation, and mathematical problem-solving. Maestro-10B inherits these strengths from its base model, Virtuoso-Lite, and further enhances them through fine-tuning on the OpenOrca dataset. This combination of a distilled base model and targeted fine-tuning makes Maestro-10B a powerful and efficient language model. overrides: parameters: model: suayptalha_Maestro-10B-Q4_K_M.gguf @@ -832,7 +832,7 @@ - https://huggingface.co/TheSkullery/L3.3-exp-unnamed-model-70b-v0.5 - https://huggingface.co/bartowski/TheSkullery_L3.3-exp-unnamed-model-70b-v0.5-GGUF description: | - No description available for this model + No description available for this model overrides: parameters: model: TheSkullery_L3.3-exp-unnamed-model-70b-v0.5-Q4_K_M.gguf @@ -1414,7 +1414,7 @@ - https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual - https://huggingface.co/bartowski/granite-embedding-107m-multilingual-GGUF description: | - Granite-Embedding-107M-Multilingual is a 107M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. This model is developed using contrastive finetuning, knowledge distillation and model merging for improved performance. + Granite-Embedding-107M-Multilingual is a 107M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. This model is developed using contrastive finetuning, knowledge distillation and model merging for improved performance. tags: - embeddings overrides: @@ -7215,7 +7215,7 @@ - https://huggingface.co/uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B - https://huggingface.co/bartowski/uncensoredai_UncensoredLM-DeepSeek-R1-Distill-Qwen-14B-GGUF description: | - An UncensoredLLM with Reasoning, what more could you want? + An UncensoredLLM with Reasoning, what more could you want? overrides: parameters: model: uncensoredai_UncensoredLM-DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf @@ -8517,9 +8517,9 @@ - https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.2.0-24b - https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.2.0-24b-GGUF description: | - This model series is intended to be multifarious in its capabilities and should be quite capable at both co-writing and roleplay as well as find itself quite at home performing sentiment analysis or summarization as part of a pipeline. + This model series is intended to be multifarious in its capabilities and should be quite capable at both co-writing and roleplay as well as find itself quite at home performing sentiment analysis or summarization as part of a pipeline. - It has been trained on a wide array of one shot instructions, multi turn instructions, tool use, role playing scenarios, text adventure games, co-writing, and much more. + It has been trained on a wide array of one shot instructions, multi turn instructions, tool use, role playing scenarios, text adventure games, co-writing, and much more. overrides: parameters: model: PocketDoc_Dans-PersonalityEngine-V1.2.0-24b-Q4_K_M.gguf @@ -8583,8 +8583,8 @@ model: BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-Q4_K_M.gguf files: - filename: BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-Q4_K_M.gguf - sha256: 689c4c75f0382421e1e691d826fe64363232f4c93453d516456d3e38189d38ea uri: huggingface://bartowski/BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-GGUF/BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-Q4_K_M.gguf + sha256: f6ae7dd8be3aedd640483ccc6895c3fc205a019246bf2512a956589c0222386e - &mudler url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models name: "LocalAI-llama3-8b-function-call-v0.2" @@ -14318,7 +14318,7 @@ - https://huggingface.co/nomic-ai/nomic-embed-text-v1.5 - https://huggingface.co/mradermacher/nomic-embed-text-v1.5-GGUF description: | - Resizable Production Embeddings with Matryoshka Representation Learning + Resizable Production Embeddings with Matryoshka Representation Learning tags: - embeddings overrides: