models(gallery): add replete-coder-instruct-8b-merged (#2782)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-12 12:15:27 +02:00 committed by GitHub
parent 41bce28d5f
commit 96127e9967
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1747,6 +1747,27 @@
- filename: Hathor_Tahsin-L3-8B-v0.85-Q4_K_M.gguf
sha256: c82f39489e767a842925fc58cafb5dec0cc71313d904a53fdb46186be899ecb0
uri: huggingface://bartowski/Hathor_Tahsin-L3-8B-v0.85-GGUF/Hathor_Tahsin-L3-8B-v0.85-Q4_K_M.gguf
- !!merge <<: *llama3
name: "replete-coder-instruct-8b-merged"
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/-0dERC793D9XeFsJ9uHbx.png
description: |
This is a Ties merge between the following models:
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
https://huggingface.co/Replete-AI/Llama3-8B-Instruct-Replete-Adapted
The Coding, and Overall performance of this models seems to be better than both base models used in the merge. Benchmarks are coming in the future.
urls:
- https://huggingface.co/Replete-AI/Replete-Coder-Instruct-8b-Merged
- https://huggingface.co/bartowski/Replete-Coder-Instruct-8b-Merged-GGUF
overrides:
parameters:
model: Replete-Coder-Instruct-8b-Merged-Q4_K_M.gguf
files:
- filename: Replete-Coder-Instruct-8b-Merged-Q4_K_M.gguf
sha256: 5374a38023b3d8617d266f94e4eff4c5d996b3197e6c42ae27315110bcc75d33
uri: huggingface://bartowski/Replete-Coder-Instruct-8b-Merged-GGUF/Replete-Coder-Instruct-8b-Merged-Q4_K_M.gguf
- name: "llama-3-sec-chat"
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
urls: