metadata
language:
- en
tags:
- mlx
- apple-silicon
- liquidai
- lfm2
- moe
- transformer
- long-context
- instruct
- quantized
- 8bit
- Mixture of Experts
- coding
- mlx
- mlx-my-repo
pipeline_tag: text-generation
library_name: mlx
license: other
license_name: lfm1.0
license_link: LICENSE
base_model: mlx-community/LFM2-8B-A1B-8bit-MLX
model-index:
- name: >-
LFM2-8B-A1B — MLX (Apple Silicon), **8-bit** (with guidance on MoE + RAM
planning)
results: []
introvoyz041/LFM2-8B-A1B-8bit-MLX-mlx-8Bit
The Model introvoyz041/LFM2-8B-A1B-8bit-MLX-mlx-8Bit was converted to MLX format from mlx-community/LFM2-8B-A1B-8bit-MLX using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/LFM2-8B-A1B-8bit-MLX-mlx-8Bit")
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)