etemiz
/

Hoopoe-8B-Llama-3.1

Model card Files Files and versions Community

Model Description

Pretrained and instruct fine tuned with faith related books and video transcripts.

Training Procedure

Ms-swift and unsloth used. LoRa with rank 32 and 128.

Sponsored by

https://pickabrain.ai

Downloads last month: 26

Safetensors

Model size

8.03B params

Tensor type

BF16

·

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for etemiz/Hoopoe-8B-Llama-3.1

Base model

meta-llama/Llama-3.1-8B

Finetuned

(900)

this model

Quantizations

1 model