mannix/qwen2.5-coder:0.5b-iq2

mannix/

qwen2.5-coder:0.5b-iq2_xs

839 Downloads Updated 9 months ago

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. I-Quant models.

tools

Updated 9 months ago

9 months ago

bb5469484721 · 324MB ·

archqwen2

parameters494M

quantizationIQ2_XS

324MB

You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

68B

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> {{- else if .M

1.6kB

Qwen 2.5 Coder series of models are now updated in 6 sizes: 0.5B, 1.5B, 3B, 7B, 14B and 32B.

Quantization from fp32
Using i-matrix calibration dataset calibration_datav3.txt
I-Quants models, only if passing tests iq2_xs, iq2_xxs, iq3_xxs, iq4_nl, iq3_s, iq2_s, iq4_xs, iq3_xs
Default quantization 7b:iq4_nl