chore(model gallery): add open-thoughts_openthinker2-32b (#5128)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-06 10:48:21 +02:00 committed by GitHub
parent 901dba6063
commit fc73b2b430
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -5650,6 +5650,23 @@
- filename: katanemo_Arch-Function-Chat-3B-Q4_K_M.gguf
sha256: f59dbef397bf1364b5f0a2c23a7f67c40ec63cc666036c4e7615fa7d79d4e1a0
uri: huggingface://bartowski/katanemo_Arch-Function-Chat-3B-GGUF/katanemo_Arch-Function-Chat-3B-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "open-thoughts_openthinker2-32b"
icon: https://huggingface.co/datasets/open-thoughts/open-thoughts-114k/resolve/main/open_thoughts.png
urls:
- https://huggingface.co/open-thoughts/OpenThinker2-32B
- https://huggingface.co/bartowski/open-thoughts_OpenThinker2-32B-GGUF
description: |
This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the OpenThoughts2-1M dataset.
The OpenThinker2-32B model is the highest performing open-data model. This model improves upon our previous OpenThinker-32B model, which was trained on 114k examples from OpenThoughts-114k. The numbers reported in the table below are evaluated with our open-source tool Evalchemy.
overrides:
parameters:
model: open-thoughts_OpenThinker2-32B-Q4_K_M.gguf
files:
- filename: open-thoughts_OpenThinker2-32B-Q4_K_M.gguf
sha256: e9c7bf7cb349cfe07b4550759a3b4d7005834d0fa7580b23e483cbfeecd7a982
uri: huggingface://bartowski/open-thoughts_OpenThinker2-32B-GGUF/open-thoughts_OpenThinker2-32B-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578