voxmenthe/internlm2_5-20b-chat_8bit
The Model voxmenthe/internlm2_5-20b-chat_8bit was converted to MLX format from internlm/internlm2_5-20b-chat using mlx-lm version 0.17.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("voxmenthe/internlm2_5-20b-chat_8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 2
Model size
6B params
Tensor type
F16
·
U32
·
Hardware compatibility
Log In
to add your hardware
Quantized