ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-18 20:27:57 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

chore(model gallery): add chronos-gold-12b-1.0

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-12-14 11:17:51 +01:00
parent fc4a714992
commit 7149f2c78d
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
gallery/index.yaml
View File

@ -4691,6 +4691,32 @@
- filename: MN-Chunky-Lotus-12B.Q4_K_M.gguf
sha256: 363defe0a769fdb715dab75517966a0a80bcdd981a610d4c759099b6c8ff143a
uri: huggingface://QuantFactory/MN-Chunky-Lotus-12B-GGUF/MN-Chunky-Lotus-12B.Q4_K_M.gguf
- !!merge <<: *mistral03
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
name: "chronos-gold-12b-1.0"
icon: https://cdn-uploads.huggingface.co/production/uploads/630417380907b9a115c6aa9f/3hc8zt8fzKdO3qHK1p1mW.webp
urls:
- https://huggingface.co/elinas/Chronos-Gold-12B-1.0
- https://huggingface.co/mradermacher/Chronos-Gold-12B-1.0-GGUF
description: |
Chronos Gold 12B 1.0 is a very unique model that applies to domain areas such as general chatbot functionatliy, roleplay, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence. The model was trained at a sequence length of 16384 (16k) and will still retain the apparent 128k context length from Mistral-Nemo, though it deteriorates over time like regular Nemo does based on the RULER Test
As a result, is recommended to keep your sequence length max at 16384, or you will experience performance degredation.
The base model is mistralai/Mistral-Nemo-Base-2407 which was heavily modified to produce a more coherent model, comparable to much larger models.
Chronos Gold 12B-1.0 re-creates the uniqueness of the original Chronos with significiantly enhanced prompt adherence (following), coherence, a modern dataset, as well as supporting a majority of "character card" formats in applications like SillyTavern.
It went through an iterative and objective merge process as my previous models and was further finetuned on a dataset curated for it.
The specifics of the model will not be disclosed at the time due to dataset ownership.
overrides:
parameters:
model: Chronos-Gold-12B-1.0.Q4_K_M.gguf
files:
- filename: Chronos-Gold-12B-1.0.Q4_K_M.gguf
sha256: d75a6ed28781f0ea6fa6e58c0b25dfecdd160d4cab64aaf511ea156e99a1e1f3
uri: huggingface://mradermacher/Chronos-Gold-12B-1.0-GGUF/Chronos-Gold-12B-1.0.Q4_K_M.gguf
- &mudler
### START mudler's LocalAI specific-models
url: "github:mudler/LocalAI/gallery/mudler.yaml@master"