metadata
base_model: HuggingFaceTB/SmolLM2-360M-Instruct
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- safetensors
- onnx
- transformers.js
- mlx
TheBlueObserver/SmolLM2-360M-Instruct-MLX
The Model TheBlueObserver/SmolLM2-360M-Instruct-MLX was converted to MLX format from HuggingFaceTB/SmolLM2-360M-Instruct using mlx-lm version 0.20.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("TheBlueObserver/SmolLM2-360M-Instruct-MLX")
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)