SmolLM2
Collection
State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M
•
15 items
•
Updated
•
184
The Model HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx was converted to MLX format from HuggingFaceTB/SmolLM2-135M-Instruct using mlx-lm version 0.19.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("HuggingFaceTB/SmolLM2-135M-Instruct-Q8-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)
Base model
HuggingFaceTB/SmolLM2-135M