From cf58a4d40cf61c21691402f8aa6cd7a41f63c596 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Wed, 9 Apr 2025 16:40:11 +0200 Subject: [PATCH] chore(model gallery): add deepcogito_cogito-v1-preview-llama-3b Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 573df8bfb152..f194d1f109b6 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2629,6 +2629,27 @@ - filename: Eximius_Persona_5B.Q4_K_M.gguf sha256: 8a8e7a0fa1068755322c51900e53423d795e57976b4d95982242cbec41141c7b uri: huggingface://mradermacher/Eximius_Persona_5B-GGUF/Eximius_Persona_5B.Q4_K_M.gguf +- !!merge <<: *llama32 + name: "deepcogito_cogito-v1-preview-llama-3b" + icon: https://huggingface.co/deepcogito/cogito-v1-preview-llama-3B/resolve/main/images/deep-cogito-logo.png + urls: + - https://huggingface.co/deepcogito/cogito-v1-preview-llama-3B + - https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF + description: | + The Cogito LLMs are instruction tuned generative models (text in/text out). All models are released under an open license for commercial use. + + Cogito models are hybrid reasoning models. Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models). + The LLMs are trained using Iterated Distillation and Amplification (IDA) - an scalable and efficient alignment strategy for superintelligence using iterative self-improvement. + The models have been optimized for coding, STEM, instruction following and general helpfulness, and have significantly higher multilingual, coding and tool calling capabilities than size equivalent counterparts. + In both standard and reasoning modes, Cogito v1-preview models outperform their size equivalent counterparts on common industry benchmarks. + Each model is trained in over 30 languages and supports a context length of 128k. + overrides: + parameters: + model: deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf + files: + - filename: deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf + sha256: 726a0ef5f818b8d238f2844f3204848bea66fb9c172b8ae0f6dc51b7bc081dd5 + uri: huggingface://bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf - &qwen25 name: "qwen2.5-14b-instruct" ## Qwen2.5 icon: https://avatars.githubusercontent.com/u/141221163