metadata
base_model: CraneAILabs/swahili-gemma-1b
language:
- en
- sw
library_name: transformers
license: gemma
tags:
- swahili
- translation
- conversational
- gemma
- gemma3
- fine-tuned
- mlx
- mlx-my-repo
pipeline_tag: text-generation
Bronsn/swahili-gemma-1b-mlx-fp16
The Model Bronsn/swahili-gemma-1b-mlx-fp16 was converted to MLX format from CraneAILabs/swahili-gemma-1b using mlx-lm version 0.26.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Bronsn/swahili-gemma-1b-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)