README.md

metadata

license: apache-2.0
language:
  - en
library_name: transformers
tags:
  - llama.cpp
  - chat
  - nlp

Qwen2-0.5B-Instruct-GGUF

Summary

Quantized Version of Qwen/Qwen2-0.5B-Instruct.

Chat template

{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>

Models

Name	Quant method	Bits	Size
Qwen2-0.5B-Instruct-Q2_K.gguf	Q2_K	2	339MB
Qwen2-0.5B-Instruct-Q3_K_L.gguf	Q3_K_L	3	369MB
Qwen2-0.5B-Instruct-Q3_K_M.gguf	Q3_K_M	3	355MB
Qwen2-0.5B-Instruct-Q3_K_S.gguf	Q3_K_S	3	338MB
Qwen2-0.5B-Instruct-Q4_0.gguf	Q4_0	4	352MB
Qwen2-0.5B-Instruct-Q4_K_M.gguf	Q4_K_M	4	398MB
Qwen2-0.5B-Instruct-Q4_K_S.gguf	Q4_K_S	4	385MB
Qwen2-0.5B-Instruct-Q5_0.gguf	Q5_0	5	397MB
Qwen2-0.5B-Instruct-Q5_K_M.gguf	Q5_K_M	5	420MB
Qwen2-0.5B-Instruct-Q5_K_S.gguf	Q5_K_S	5	413MB
Qwen2-0.5B-Instruct-Q6_K.gguf	Q6_K	6	506MB
Qwen2-0.5B-Instruct-Q8_0.gguf	Q8_0	8	531MB