README.md

metadata

library_name: transformers
license: gpl-3.0
language:
  - as
  - bn
  - brx
  - doi
  - gom
  - gu
  - en
  - hi
  - kn
  - ks
  - mai
  - ml
  - mni
  - mr
  - ne
  - or
  - pa
  - sa
  - sat
  - sd
  - ta
  - te
  - ur
base_model: sarvamai/sarvam-translate
base_model_relation: finetune
pipeline_tag: translation
tags:
  - mlx

mlx-community/sarvam-translate-mlx-bf16

The Model mlx-community/sarvam-translate-mlx-bf16 was converted to MLX format from sarvamai/sarvam-translate using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("bibproj/sarvam-translate-mlx-fp16")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)