428 5 months ago

Turkcell-LLM-7b-v1 is a Turkish-optimized large language model based on Mistral 7B, fine-tuned with DORA and LORA methods on 5 billion Turkish tokens. Designed for robust natural language understanding and generation, it features an extended tokenizer

37761a621050 · 134B
{{- if .System }}
<|im_start|>system {{ .System }}<|im_end|>
{{- end }}
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant