Text Generation
MLX
Safetensors
Hungarian
llama
hungarian
emese
from-scratch
base-model
apple-silicon
Instructions to use emese-tech/er with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use emese-tech/er 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("emese-tech/er") 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 emese-tech/er with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "emese-tech/er" --prompt "Once upon a time"
- Atomic Chat
Download tokenizer.model from emese-tech/er: direct link, hf CLI and curl.
- Browser
- Download file 845 kB
-
https://huggingface.co/emese-tech/er/resolve/main/tokenizer.model
- Command line
-
hf download hf://emese-tech/er/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/emese-tech/er/resolve/main/tokenizer.model
845 kB
- Xet hash:
- e57b1f6fbd9e6599290bc7ad9b7534ed4ac04956a0885deb21ece49d85b022cf
- Size of remote file:
- 845 kB
- SHA256:
- 244bb6facd57b3890990261b9932ab50d79630d5b35058c902a5c96c32fa2950
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.