Instructions to use joseluissaorin/talkie-1930-13b-it-mlx-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use joseluissaorin/talkie-1930-13b-it-mlx-q8 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("joseluissaorin/talkie-1930-13b-it-mlx-q8") 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 joseluissaorin/talkie-1930-13b-it-mlx-q8 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "joseluissaorin/talkie-1930-13b-it-mlx-q8" --prompt "Once upon a time"
- Atomic Chat
Download model-00007-of-00007.safetensors from joseluissaorin/talkie-1930-13b-it-mlx-q8: direct link, hf CLI and curl.
- Browser
- Download file 558 MB
-
https://huggingface.co/joseluissaorin/talkie-1930-13b-it-mlx-q8/resolve/main/model-00007-of-00007.safetensors
- Command line
-
hf download hf://joseluissaorin/talkie-1930-13b-it-mlx-q8/model-00007-of-00007.safetensors
-
curl -L -o model-00007-of-00007.safetensors https://huggingface.co/joseluissaorin/talkie-1930-13b-it-mlx-q8/resolve/main/model-00007-of-00007.safetensors
558 MB
- Xet hash:
- 4f067e3793fb5850be267c4008e801a04261b5bcfbe717ecc1bd34687b9e47b7
- Size of remote file:
- 558 MB
- SHA256:
- 612d3a6f2f6ad605331ac28d32e47e8bd10f2a1c446d046bc91bb8df16cef45e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.