promptnow/
thalle-0.1-7b-fa-q4_k_m:latest

13 1 year ago

Unofficial THaLLE-0.1-7B-fa Q4_K_M Quantization (https://huggingface.co/KBTG-Labs/THaLLE-0.1-7B-fa)

1 year ago

641c321405c7 · 4.7GB ·

model
qwen2
·
7.62B
·
Q4_K_M
params
{ "stop": [ "<|im_start|>", "<|im_end|>" ] }
template
{{- range .Messages }}<|im_start|>{{ .Role }} {{ .Content }}<|im_end|> {{ end }}<|im_start|>assistan

Readme

This model is a Qwen2-7B-Instruct fine-tuned on our Internal CFA Mock Exam 2009-2019 containing 9,426 Questions using LoRA.