metadata
library_name: mlx
tags:
- falcon-h1
- edge
- mlx
license: other
license_name: falcon-llm-license
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
base_model: tiiuae/Falcon-H1-Tiny-Multilingual-100M-Base
pipeline_tag: text-generation
mlx-community/Falcon-H1-Tiny-Multilingual-100M-Base-4bit
This model mlx-community/Falcon-H1-Tiny-Multilingual-100M-Base-4bit was converted to MLX format from tiiuae/Falcon-H1-Tiny-Multilingual-100M-Base using mlx-lm version 0.30.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Falcon-H1-Tiny-Multilingual-100M-Base-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)