vihangd/smartyplats-1.1b-v1-GGUF

Quantized GGUF model files for smartyplats-1.1b-v1 from vihangd

Name	Quant method	Size
smartyplats-1.1b-v1.q2_k.gguf	q2_k	482.14 MB
smartyplats-1.1b-v1.q3_k_m.gguf	q3_k_m	549.85 MB
smartyplats-1.1b-v1.q4_k_m.gguf	q4_k_m	667.81 MB
smartyplats-1.1b-v1.q5_k_m.gguf	q5_k_m	782.04 MB
smartyplats-1.1b-v1.q6_k.gguf	q6_k	903.41 MB
smartyplats-1.1b-v1.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

SmartyPlats-1.1b V1

An experimental finetune of TinyLLaMA 1T with QLoRA

Datasets

Trained on alpca style datasets

Prompt Template

Uses alpaca style prompt template