Omoeba/gpt-oss-coder:20b

Omoeba/ gpt-oss-coder:20b

2,180 Downloads Updated 3 months ago

gpt-oss optimized for coding, now with an increased 128k context length

tools thinking 20b

ollama run Omoeba/gpt-oss-coder:20b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Omoeba/gpt-oss-coder:20b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Omoeba/gpt-oss-coder:20b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Omoeba/gpt-oss-coder:20b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 months ago

3 months ago

f4b37a278cc2 · 14GB ·

model

archgptoss

parameters20.9B

quantizationMXFP4

14GB

license

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

11kB

params

{ "num_ctx": 131072, "temperature": 1 }

35B

template

<|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI. Knowledge cutof

7.2kB

Readme

Make sure to use ollama version 0.11.5 or later to avoid out-of-memory issues. The new 128k version running on 0.11.5 has roughly the same memory usage as the previous 64k version on 0.11.4.