ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-04-13 06:03:09 +00:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity

models(gallery): add replete-llm-v2.5-qwen-7b (#3689)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-09-29 22:47:26 +02:00 committed by GitHub
parent 1689740269
commit ad62156d54
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
gallery/index.yaml
View File

@ -254,6 +254,24 @@
- filename: Replete-LLM-V2.5-Qwen-14b-Q4_K_M.gguf
sha256: 17d0792ff5e3062aecb965629f66e679ceb407e4542e8045993dcfe9e7e14d9d
uri: huggingface://bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF/Replete-LLM-V2.5-Qwen-14b-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "replete-llm-v2.5-qwen-7b"
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ihnWXDEgV-ZKN_B036U1J.png
urls:
- https://huggingface.co/Replete-AI/Replete-LLM-V2.5-Qwen-7b
- https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-7b-GGUF
description: |
Replete-LLM-V2.5-Qwen-7b is a continues finetuned version of Qwen2.5-14B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the Ties merge method
This version of the model shows higher performance than the original instruct and base models.
overrides:
parameters:
model: Replete-LLM-V2.5-Qwen-7b-Q4_K_M.gguf
files:
- filename: Replete-LLM-V2.5-Qwen-7b-Q4_K_M.gguf
sha256: 054d54972259c0398b4e0af3f408f608e1166837b1d7535d08fc440d1daf8639
uri: huggingface://bartowski/Replete-LLM-V2.5-Qwen-7b-GGUF/Replete-LLM-V2.5-Qwen-7b-Q4_K_M.gguf
- &smollm
## SmolLM
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"