metadata
license: mpl-2.0
library_name: transformers
tags:
- gemma-3
- synthetic-data
- textbooks
- distillation
- utility
- summarization
- lightning
- conversational
- mlx
- mlx-my-repo
base_model: TitleOS/Spark-270M-FP16
datasets:
- TitleOS/Spark-Lightning-Synthetic-Textbooks
language:
- en
pipeline_tag: text-generation
bradyclarke/Spark-270M-FP16-mlx-6Bit
The Model bradyclarke/Spark-270M-FP16-mlx-6Bit was converted to MLX format from TitleOS/Spark-270M-FP16 using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("bradyclarke/Spark-270M-FP16-mlx-6Bit")
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)