This is a finetune of the Llama 3.2 3B with the default lollms style. The finetune used the lollms aware database that contains information about lollms. Using this model in lollms reduces the need to add context information to the prompt.

Downloads last month
65
GGUF
Model size
3.21B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ParisNeo/LLama-3.2-3B-Lollms-Finetuned-GGUF

Quantized
(321)
this model

Dataset used to train ParisNeo/LLama-3.2-3B-Lollms-Finetuned-GGUF

Space using ParisNeo/LLama-3.2-3B-Lollms-Finetuned-GGUF 1