mlx-community/sarvam-translate-mlx-4bit

This model mlx-community/sarvam-translate-mlx-4bit was converted to MLX format from sarvamai/sarvam-translate using mlx-lm version 0.25.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/sarvam-translate-mlx-4bit")

def translate(lang, text):
    return f"""<bos><start_of_turn>user
    Translate the text below to {lang}.
    
    {text}<end_of_turn>
    """

generate(
    model,
    tokenizer,
    prompt=translate("Kannada", "How are you?"),
    verbose=True
)

# Output:
# ನೀವು ಹೇಗಿದ್ದೀರಿ?
Downloads last month
43
Safetensors
Model size
711M params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlx-community/sarvam-translate-mlx-4bit

Quantized
(3)
this model