kaizu/
bn_chat_2:latest

14 1 year ago

Fine-tuned version of llama2-v0.1-instruct from BanglaLLM in huggingface. Quantized to 4bit -> q4_k_m using llama.cpp. Trained on 2 * T4.

... /
template
4c0b305efed0 · 129B
[INST]<<SYS>>{{ .System }}<</SYS>>
[INST]### Instruction:
{{ .Prompt }}[/INST]
### Input:
### Response:
{{ .Response}}[/INST]