Text Generation
NeMo
Safetensors
MLX
English
mistral
sft
unsloth
style-tune
roleplay
creative
12b
mlx-my-repo
conversational
5-bit
Instructions to use ewald1976/Silver-Siren-ST-12B-mlx-5Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use ewald1976/Silver-Siren-ST-12B-mlx-5Bit with NeMo:
# tag did not correspond to a valid NeMo domain.
- MLX
How to use ewald1976/Silver-Siren-ST-12B-mlx-5Bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("ewald1976/Silver-Siren-ST-12B-mlx-5Bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Unsloth Desktop
- MLX LM
How to use ewald1976/Silver-Siren-ST-12B-mlx-5Bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "ewald1976/Silver-Siren-ST-12B-mlx-5Bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "ewald1976/Silver-Siren-ST-12B-mlx-5Bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ewald1976/Silver-Siren-ST-12B-mlx-5Bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Download tokenizer.json from ewald1976/Silver-Siren-ST-12B-mlx-5Bit: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/ewald1976/Silver-Siren-ST-12B-mlx-5Bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://ewald1976/Silver-Siren-ST-12B-mlx-5Bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/ewald1976/Silver-Siren-ST-12B-mlx-5Bit/resolve/main/tokenizer.json
17.1 MB
- Xet hash:
- 8d2c2f0daa05743d54717aff085f129fa44dfcafb6aeeeca4a819ef91df7c0db
- Size of remote file:
- 17.1 MB
- SHA256:
- 33cb74e9ca1c0323b1be5f7e367b96bae218c22d0c4ed5b0edeec39f3a8755c3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.