Text Generation
MLX
Safetensors
English
llama
Supra
Project-Chimera
chimera
QnA
GPT
CPU
tiny
SLM
open
open-source
50M
3-bit
Instructions to use usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit" --prompt "Once upon a time"
usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit
The Model usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit was converted to MLX format from SupraLabs/Supra-1.5-50M-Instruct-exp using mlx-lm version 0.31.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit")
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
- 17
Model size
6.48M params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
3-bit
Model tree for usermma/Supra-1.5-50M-Instruct-exp-mlx-3bit
Base model
SupraLabs/Supra-50M-Base Finetuned
SupraLabs/Supra-1.5-50M-Base-exp Finetuned
SupraLabs/Supra-1.5-50M-Instruct-exp