Views
No views yet
1vllm serve cyberneurova/cyberneurova-Qwen3.8-27B \
2 --max-model-len 65536 --trust-remote-code1from openai import OpenAI
2client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")
3
4r = client.chat.completions.create(
5 model="cyberneurova/cyberneurova-Qwen3.8-27B",
6 messages=[{"role": "user", "content": "Write a Python function to parse a CSV."}],
7 max_tokens=2000,
8)
9print(r.choices[0].message.content)1from openai import OpenAI
2client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")
3
4r = client.chat.completions.create(
5 model="cyberneurova/cyberneurova-Qwen3.8-27B",
6 messages=[{"role": "user", "content": [
7 {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
8 {"type": "text", "text": "What's in this image?"},
9 ]}],
10 max_tokens=1000,
11)
12print(r.choices[0].message.content)image_url also accepts a data:image/png;base64,... data URI for local images.
Running locally with llama.cpp / Ollama? Use the GGUF build plus its vision
projector: cyberneurova-Qwen3.8-27B-GGUF
(mmproj-F16.gguf).You are a direct technical assistant. Answer the question and nothing else.max_tokens to at least 1500 (2000–4000 for code),
or long answers may be cut off.