Instructions to use AlexWortega/lfm2-physics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AlexWortega/lfm2-physics with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use AlexWortega/lfm2-physics with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for AlexWortega/lfm2-physics to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for AlexWortega/lfm2-physics to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for AlexWortega/lfm2-physics to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="AlexWortega/lfm2-physics", max_seq_length=2048, )
| { | |
| "stage": 3, | |
| "timestamp": "2026-02-04T14:24:05.704295", | |
| "config": { | |
| "data_dir": "data/train", | |
| "output_dir": "checkpoints/lfm2-physics", | |
| "epochs_per_stage": 1, | |
| "batch_size": 2, | |
| "grad_accum": 8, | |
| "lr": 0.0002, | |
| "max_seq_length": 4096, | |
| "curriculum_stages": 5, | |
| "max_examples_per_stage": 1000, | |
| "max_context_frames": 5, | |
| "physics_loss_weight": 0.01, | |
| "resume": null, | |
| "wandb_project": "physics-llm", | |
| "wandb_offline": false, | |
| "lora_r": 32, | |
| "lora_alpha": 64, | |
| "model": "LiquidAI/LFM2-350M", | |
| "timestamp": "2026-02-04T14:11:22.835795" | |
| }, | |
| "metrics": { | |
| "train_runtime": 148.7076, | |
| "train_samples_per_second": 6.725, | |
| "train_steps_per_second": 0.424, | |
| "total_flos": 7086689746944000.0, | |
| "train_loss": 1.0771233959803506, | |
| "epoch": 1.0, | |
| "step": 63 | |
| } | |
| } |