Compact code-specialized model for lightweight applications
Part of the Qwen 2.5 Coder series, optimized for code generation, reasoning, and fixing. The 0.5B model offers a balanced combination of performance and efficiency.
494 M
32k tokens
Perfect for lightweight coding applications, prototyping, and quick development tasks.
Multilingual code support across 40+ programming languages
Installation:
pip install tinfoil
Inference:
from tinfoil import TinfoilAI
client = TinfoilAI(
enclave="models.default.tinfoil.sh",
repo="tinfoilsh/default-models-nitro",
api_key="YOUR_API_KEY",
)
chat_completion = client.chat.completions.create(
messages=[
{
"role": "user",
"content": "Hello!",
}
],
model="qwen2.5-coder-0.5b",
)
print(chat_completion.choices[0].message.content)