models(gallery): add llama-3.2-3b-agent007 (#3781)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-10 19:06:58 +02:00 committed by GitHub
parent 6e78d8cd9d
commit ad5e7d376a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -143,6 +143,19 @@
- filename: Llama3.2-3B-Esper2.Q4_K_M.gguf
sha256: 11d2bd674aa22a71a59ec49ad29b695000d14bc275b0195b8d7089bfc7582fc7
uri: huggingface://QuantFactory/Llama3.2-3B-Esper2-GGUF/Llama3.2-3B-Esper2.Q4_K_M.gguf
- !!merge <<: *llama32
name: "llama-3.2-3b-agent007"
urls:
- https://huggingface.co/QuantFactory/Llama-3.2-3B-Agent007-GGUF
description: |
The model is a quantized version of EpistemeAI/Llama-3.2-3B-Agent007, developed by EpistemeAI and fine-tuned from unsloth/llama-3.2-3b-instruct-bnb-4bit. It was trained 2x faster with Unsloth and Huggingface's TRL library. Fine tuned with Agent datasets.
overrides:
parameters:
model: Llama-3.2-3B-Agent007.Q4_K_M.gguf
files:
- filename: Llama-3.2-3B-Agent007.Q4_K_M.gguf
sha256: 7a2543a69b116f2a059e2e445e5d362bb7df4a51b97e83d8785c1803dc9d687f
uri: huggingface://QuantFactory/Llama-3.2-3B-Agent007-GGUF/Llama-3.2-3B-Agent007.Q4_K_M.gguf
- &qwen25
## Qwen2.5
name: "qwen2.5-14b-instruct"