mannix/qwen2.5-coder:7b-iq3

mannix/ qwen2.5-coder:7b-iq3_s

1,002 Downloads Updated 1 year ago

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

tools

ollama run mannix/qwen2.5-coder:7b-iq3_s

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mannix/qwen2.5-coder:7b-iq3_s",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mannix/qwen2.5-coder:7b-iq3_s',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mannix/qwen2.5-coder:7b-iq3_s',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

7fe0e50201b3 · 3.5GB ·

model

archqwen2

parameters7.62B

quantizationIQ3_S

3.5GB

template

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

1.6kB

system

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

68B

license

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

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

Model description