models(gallery): add azure_dusk-v0.2-iq-imatrix ()

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-09-13 19:48:54 +02:00 committed by GitHub
parent 7fe6d0ad2b
commit 5213e79f5c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -658,6 +658,23 @@
- filename: Mahou-1.3-llama3.1-8B.Q4_K_M.gguf
sha256: 88bfdca2f6077d789d3e0f161d19711aa208a6d9a02cce96a2276c69413b3594
uri: huggingface://mradermacher/Mahou-1.3-llama3.1-8B-GGUF/Mahou-1.3-llama3.1-8B.Q4_K_M.gguf
- !!merge <<: *llama31
name: "azure_dusk-v0.2-iq-imatrix"
# chatml
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/n3-g_YTk3FY-DBzxXd28E.png
urls:
- https://huggingface.co/Lewdiculous/Azure_Dusk-v0.2-GGUF-IQ-Imatrix
description: |
"Following up on Crimson_Dawn-v0.2 we have Azure_Dusk-v0.2! Training on Mistral-Nemo-Base-2407 this time I've added significantly more data, as well as trained using RSLoRA as opposed to regular LoRA. Another key change is training on ChatML as opposed to Mistral Formatting."
by Author.
overrides:
parameters:
model: Azure_Dusk-v0.2-Q4_K_M-imat.gguf
files:
- filename: Azure_Dusk-v0.2-Q4_K_M-imat.gguf
sha256: c03a670c00976d14c267a0322374ed488b2a5f4790eb509136ca4e75cbc10cf4
uri: huggingface://Lewdiculous/Azure_Dusk-v0.2-GGUF-IQ-Imatrix/Azure_Dusk-v0.2-Q4_K_M-imat.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"