hisparshmishra1/ fast-qwen:latest

65 1 week ago

Qwen2.5-1.5B-Instruct (Q4_K_M), tuned for fast local inference — 5.4x faster than the original with verified quality (perplexity +3%, task scores unchanged).

... /
template
62fbfd9ed093 · 182B
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>