vihangd/dopeyplats-1.1b-2T-v1-GGUF

Quantized GGUF model files for dopeyplats-1.1b-2T-v1 from vihangd

Name	Quant method	Size
dopeyplats-1.1b-2t-v1.fp16.gguf	fp16	2.20 GB
dopeyplats-1.1b-2t-v1.q2_k.gguf	q2_k	483.12 MB
dopeyplats-1.1b-2t-v1.q3_k_m.gguf	q3_k_m	550.82 MB
dopeyplats-1.1b-2t-v1.q4_k_m.gguf	q4_k_m	668.79 MB
dopeyplats-1.1b-2t-v1.q5_k_m.gguf	q5_k_m	783.02 MB
dopeyplats-1.1b-2t-v1.q6_k.gguf	q6_k	904.39 MB
dopeyplats-1.1b-2t-v1.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

DopeyPlats-1.1b V2

An experimental finetune of TinyLLaMA 1.1b 2T with Alpaca-QLoRA with some dpo goodness

Datasets

Trained on alpca style datasets

Prompt Template

Uses alpaca style prompt template