chore(model gallery): add helpingai_helpingai3-raw (#5070)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-25 10:09:00 +01:00 committed by GitHub
parent 5d2c53abc0
commit 747eeb1d46
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -5117,6 +5117,20 @@
- filename: qwen-writerdemo-7b-s500.i1-Q4_K_M.gguf
sha256: dcc0e2dd36587fdd3ed0c8e8c215a01244f00dd85f62da23642410d0e688fe13
uri: huggingface://mradermacher/qwen-writerdemo-7b-s500-i1-GGUF/qwen-writerdemo-7b-s500.i1-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "helpingai_helpingai3-raw"
urls:
- https://huggingface.co/HelpingAI/Helpingai3-raw
- https://huggingface.co/bartowski/HelpingAI_Helpingai3-raw-GGUF
description: |
The LLM model described is an emotionally intelligent, conversational and EQ-focused model developed by HelpingAI. It is based on the Helpingai3-raw model and has been quantized using the llama.cpp framework. The model is available in various quantization levels, allowing for different trade-offs between performance and size. Users can choose the appropriate quantization level based on their available RAM, VRAM, and desired performance. The model's weights are provided in .gguf format and can be downloaded from the Hugging Face model repository.
overrides:
parameters:
model: HelpingAI_Helpingai3-raw-Q4_K_M.gguf
files:
- filename: HelpingAI_Helpingai3-raw-Q4_K_M.gguf
sha256: de7a223ad397ba27c889dad08466de471166f1e76962b855c72cf6b779a7b857
uri: huggingface://bartowski/HelpingAI_Helpingai3-raw-GGUF/HelpingAI_Helpingai3-raw-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578