Instructions to use laukerry/AntAngelMed-mlx-8Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use laukerry/AntAngelMed-mlx-8Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir AntAngelMed-mlx-8Bit laukerry/AntAngelMed-mlx-8Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
laukerry/AntAngelMed-mlx-8Bit
The Model laukerry/AntAngelMed-mlx-8Bit was converted to MLX format from MedAIBase/AntAngelMed using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("laukerry/AntAngelMed-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)
- Downloads last month
- 32
Model size
103B params
Tensor type
F16
路
U32 路
F32 路
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
Model tree for laukerry/AntAngelMed-mlx-8Bit
Base model
inclusionAI/Ling-flash-base-2.0 Finetuned
inclusionAI/Ling-flash-2.0 Finetuned
MedAIBase/AntAngelMed