ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-11 21:12:58 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

chore(model gallery): add deepcogito_cogito-v1-preview-llama-3b (#5148)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-09 16:42:53 +02:00 committed by GitHub
parent 5a8a2adb44
commit 673e59e76c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
gallery/index.yaml
View File

@ -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