Text Generation
MLX
English
sol_lassi
causal-lm
decoder-only
small-language-model
experimental
sol-intelligence
Instructions to use solintellegence/Sol-Lassi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use solintellegence/Sol-Lassi 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("solintellegence/Sol-Lassi") 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 solintellegence/Sol-Lassi with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "solintellegence/Sol-Lassi" --prompt "Once upon a time"
- Atomic Chat
Download config.json from solintellegence/Sol-Lassi: direct link, hf CLI and curl.
- Browser
- Download file 370 Bytes
-
https://huggingface.co/solintellegence/Sol-Lassi/resolve/main/config.json
- Command line
-
hf download hf://solintellegence/Sol-Lassi/config.json
-
curl -L -o config.json https://huggingface.co/solintellegence/Sol-Lassi/resolve/main/config.json
370 Bytes
| { | |
| "model_type": "sol_lassi", | |
| "architectures": ["SolLassi"], | |
| "model_name": "Sol Lassi 600K Base", | |
| "parameter_count": 600000, | |
| "vocab_size": 2048, | |
| "hidden_size": 96, | |
| "num_hidden_layers": 6, | |
| "num_attention_heads": 3, | |
| "head_dim": 32, | |
| "intermediate_size": 104, | |
| "max_position_embeddings": 128, | |
| "tie_word_embeddings": true, | |
| "model_format": "mlx_npz" | |
| } | |