chore(model): add magnum-12b-v2.5-kto-i1 to the gallery (#4151)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-14 15:38:00 +01:00 committed by GitHub
parent 1770b92fb6
commit 065215341f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -3499,6 +3499,21 @@
- filename: Mistral-Nemo-Prism-12B-Q4_K_M.gguf - filename: Mistral-Nemo-Prism-12B-Q4_K_M.gguf
sha256: 96b922c6d55d94ffb91e869b8cccaf2b6dc449d75b1456f4d4578c92c8184c25 sha256: 96b922c6d55d94ffb91e869b8cccaf2b6dc449d75b1456f4d4578c92c8184c25
uri: huggingface://bartowski/Mistral-Nemo-Prism-12B-GGUF/Mistral-Nemo-Prism-12B-Q4_K_M.gguf uri: huggingface://bartowski/Mistral-Nemo-Prism-12B-GGUF/Mistral-Nemo-Prism-12B-Q4_K_M.gguf
- !!merge <<: *mistral03
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
name: "magnum-12b-v2.5-kto-i1"
icon: https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/sWYs3iHkn36lw6FT_Y7nn.png
urls:
- https://huggingface.co/mradermacher/magnum-12b-v2.5-kto-i1-GGUF
description: |
v2.5 KTO is an experimental release; we are testing a hybrid reinforcement learning strategy of KTO + DPOP, using rejected data sampled from the original model as "rejected". For "chosen", we use data from the original finetuning dataset as "chosen". This was done on a limited portion of of primarily instruction following data; we plan to scale up a larger KTO dataset in the future for better generalization. This is the 5th in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of anthracite-org/magnum-12b-v2.
overrides:
parameters:
model: magnum-12b-v2.5-kto.i1-Q4_K_M.gguf
files:
- filename: magnum-12b-v2.5-kto.i1-Q4_K_M.gguf
sha256: 07e91d2c6d4e42312e65a69c54f16be467575f7a596fe052993b388e38b90d76
uri: huggingface://mradermacher/magnum-12b-v2.5-kto-i1-GGUF/magnum-12b-v2.5-kto.i1-Q4_K_M.gguf
- &mudler - &mudler
### START mudler's LocalAI specific-models ### START mudler's LocalAI specific-models
url: "github:mudler/LocalAI/gallery/mudler.yaml@master" url: "github:mudler/LocalAI/gallery/mudler.yaml@master"