Edit model card

Model Card for TarsDolly

Model Details

TarsDolly is FT on HuggingFaceH4/zephyr-7b-alpha using Dolly-15k dataset for general chat.

Preprocessing

Dolly-15k dataset was converted into chatml style for futher FT on zephyr-7b-beta model

Training Hyperparameters

epochs 4 batch_size 1 block_size 2096 lr 2e-4

Downloads last month
0
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference API
Input a message to start chatting with xriminact/TarsDolly.
Inference API (serverless) does not yet support adapter-transformers models for this pipeline type.

Dataset used to train xriminact/TarsDolly