Llama 3.2 1B logo

Llama 3.2 1B

Multilingual large language model optimized for dialogue

Model Details

The Meta Llama 3.2 1B model is optimized for multilingual dialogue use cases, including personal information management, knowledge retrieval, and rewriting tasks running locally on edge devices. It is competitive with other 1-3B parameter models.

Parameters

1.24 billion

Context Window

128k tokens

Recommended Use

Best suited for personal information management, multilingual knowledge retrieval, and rewriting tasks running locally on edge.

Supported Languages

English, French, German, Hindi, Italian, Portuguese, Spanish, Thai

Usage Examples

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="llama3.2-1b",
)
print(chat_completion.choices[0].message.content)
Tinfoil IconTinfoil