README.md

metadata

base_model: tiiuae/Falcon3-7B-Instruct-1.58bit
library_name: mlx
license: other
license_name: falcon-llm-license
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
tags:
  - bitnet
  - falcon3
  - mlx
pipeline_tag: text-generation

mlx-community/Falcon3-7B-Instruct-1.58bit-8bit

This model mlx-community/Falcon3-7B-Instruct-1.58bit-8bit was converted to MLX format from tiiuae/Falcon3-7B-Instruct-1.58bit using mlx-lm version 0.25.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Falcon3-7B-Instruct-1.58bit-8bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)