ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-01-29 15:44:17 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

chore(model gallery): add chuluun-qwen2.5-72b-v0.01 (#4573)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-01-10 16:27:22 +01:00 committed by GitHub
parent 0d08aaa29b
commit 6e34430d99
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

@ -2922,6 +2922,27 @@
- filename: HuatuoGPT-o1-7B-v0.1-Q4_K_M.gguf
sha256: 8fc4b797a532d67d677e90293175ff1365c91677d06ea27af297bdf5b60c2d1d
uri: huggingface://bartowski/HuatuoGPT-o1-7B-v0.1-GGUF/HuatuoGPT-o1-7B-v0.1-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "chuluun-qwen2.5-72b-v0.01"
icon: https://huggingface.co/DatToad/Chuluun-Qwen2.5-72B-v0.01/resolve/main/00008-1523559621.png
urls:
- https://huggingface.co/DatToad/Chuluun-Qwen2.5-72B-v0.01
- https://huggingface.co/bartowski/Chuluun-Qwen2.5-72B-v0.01-GGUF
description: |
This is a merge of pre-trained language models created using mergekit.
The models in this merge are some of my favorites and I found I liked all of them for different reasons. I believe this model is greater than the sum of its parts - it has the storywriting and language of Eva and Kunou, the spiciness of Magnum, and the uncensored intelligence of Tess. It excels in handling multiple characters and keeping their thoughts, speech, and actions separate, including scene changes. It also appears to match dialogue well to the characters and their backgrounds.
Model_stock was the method used, it's very straightforward and quite fast, the bottleneck seemed to be my NVMe drive.
All source models use ChatML prompt formatting and it responds very well. For testing purposes I am using a temperature of 1.08, rep pen of 0.03, and DRY with 0.6 (most Qwen models seem to need DRY). All other samplers are neutralized.
overrides:
parameters:
model: Chuluun-Qwen2.5-72B-v0.01-Q4_K_M.gguf
files:
- filename: Chuluun-Qwen2.5-72B-v0.01-Q4_K_M.gguf
sha256: 901d9d10aad42de3188e721accdc4eb0efec96cbca48563f802793dceaf551f5
uri: huggingface://bartowski/Chuluun-Qwen2.5-72B-v0.01-GGUF/Chuluun-Qwen2.5-72B-v0.01-Q4_K_M.gguf
- &smollm
## SmolLM
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"