The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. I-Quant models.
tools
530 Pulls Updated 3 months ago
Updated 3 months ago
3 months ago
68af2cd13aa9 · 4.4GB
model
archqwen2
·
parameters7.62B
·
quantizationIQ4_NL
4.4GB
system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.
68B
template
{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
{{- else if .M
1.6kB
license
Apache License
Version 2.0, January 200
11kB
Readme
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