Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).
1.5b
7b
72b
107.6K Pulls Updated 3 months ago
Updated 3 months ago
3 months ago
6ae803c94afe · 55GB
model
archqwen2
·
parameters72.7B
·
quantizationQ5_1
55GB
params
{
"stop": [
"<|im_start|>",
"<|im_end|>"
]
}
59B
template
{{- range .Messages }}<|im_start|>{{ .Role }}
{{ .Content }}<|im_end|>
{{- end }}<|im_start|>assista
102B
license
Apache License
Version 2.0, January 2004
11kB
Readme
Qwen2 Math features 3 model sizes (1.5B, 7B, and 72B) each with a base model, for completion, few-shot inference, and fine-tuning, and an instruct model for chatting.