---
license: apache-2.0
base_model: LiquidAI/LFM2-350M
library_name: peft
pipeline_tag: text-generation
tags:
- physics
- scenarios
- next-frame-prediction
- lora
- sft
- trl
- unsloth
- icml-2026
---

# lfm2-scenarios

Sister checkpoint to [lfm2-physics](https://huggingface.co/AlexWortega/lfm2-physics) — LoRA fine-tune of `LiquidAI/LFM2-350M` on the physics scenarios dataset, with a different training regime / curriculum sampling.

## Adapter details

- **Base**: `LiquidAI/LFM2-350M`
- **Adapter type**: LoRA, r=32, alpha=64, dropout=0.0
- **Target modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
- **Trainer**: `SFTTrainer` (TRL) via Unsloth
- **Curriculum**: 5 stages, includes scenario-type stratified sampling
- **Task**: autoregressive next-frame prediction; conditioning includes scenario Type, Difficulty, Static geometry, Constraints

## Stages

- `stage0/` ... `stage4/` — checkpoints from each curriculum stage
- `final/` — final adapter

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-350M")
model = PeftModel.from_pretrained(base, "AlexWortega/lfm2-scenarios", subfolder="final")
tokenizer = AutoTokenizer.from_pretrained("AlexWortega/lfm2-scenarios", subfolder="final")
```

## Training data

900K scenes, 24 seen scenario types (avalanche, basketball, billiards, breakout, bridge, chain, conveyor, dominos, explosion, funnel, head_on, jenga, marble_run, orbit, pendulum, pinball, plinko, projectile, pyramid, seesaw, ski_jump, tower, wind, wrecking_ball). 6 types held out for OOD eval (pong, bowling, ramp_roll, angry_birds, hourglass, newtons_cradle).

## Citation

ICML-2026 submission (in progress).