Text Generation
MLX
Safetensors
English
llama
optiq
quantized
mixed-precision
4bit
8bit
apple-silicon
edit-prediction
next-edit-suggestion
code
autocomplete
fim
4-bit precision
Instructions to use bouroo/zeta-2.1-OptiQ-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use bouroo/zeta-2.1-OptiQ-4 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("bouroo/zeta-2.1-OptiQ-4") 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 bouroo/zeta-2.1-OptiQ-4 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "bouroo/zeta-2.1-OptiQ-4" --prompt "Once upon a time"
- Atomic Chat
Download generation_config.json from bouroo/zeta-2.1-OptiQ-4: direct link, hf CLI and curl.
- Browser
- Download file 180 Bytes
-
https://huggingface.co/bouroo/zeta-2.1-OptiQ-4/resolve/main/generation_config.json
- Command line
-
hf download hf://bouroo/zeta-2.1-OptiQ-4/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/bouroo/zeta-2.1-OptiQ-4/resolve/main/generation_config.json
180 Bytes
| { | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "pad_token_id": 1, | |
| "do_sample": true, | |
| "temperature": 0.2, | |
| "top_p": 0.95, | |
| "max_new_tokens": 128, | |
| "repetition_penalty": 1.0 | |
| } | |