qwen2-math:7b-instruct-q2

qwen2-math:7b-instruct-q2_K

356.5K Downloads Updated 1 year ago

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

ollama run qwen2-math:7b-instruct-q2_K

curl http://localhost:11434/api/chat \
  -d '{
    "model": "qwen2-math:7b-instruct-q2_K",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='qwen2-math:7b-instruct-q2_K',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'qwen2-math:7b-instruct-q2_K',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

4ed0c248a5bf · 3.0GB ·

model

archqwen2

parameters7.62B

quantizationQ2_K

3.0GB

license

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

11kB

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

template

{{- range .Messages }}<|im_start|>{{ .Role }} {{ .Content }}<|im_end|> {{- end }}<|im_start|>assista

102B

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.

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).

Details

Readme

References: