Downloads · 30 days
0
Pi-Lumine-4B-FlowMatching
AntimLabs/Pi-Lumine-4B-FlowMatching
Pi-Lumine-4B-FlowMatching is a machine learning model from AntimLabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
A Pi0.5-style flow-matching action decoder trained on top of a frozen Qwen3.5-4B VLM backbone.
Access
Public
Updated Apr 12, 2026
Repo size
2.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt256 MB · 93%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026
- SHA
- 62d67945
Base models
Model card
From the Hugging Face model README
Pi-Lumine 4B — Flow-Matching Action Decoder for Elden Ring
A Pi0.5-style flow-matching action decoder trained on top of a frozen Qwen3.5-4B VLM backbone.
Architecture
- Base VLM: Qwen/Qwen3.5-4B (frozen, not included — downloaded at runtime)
- Action Decoder: FiLM-conditioned transformer with cross-attention to VLM hidden states
- 2 decoder layers, VLM dim 2560 → decoder dim 1024, 8 attention heads
- Projection layers decouple decoder from VLM hidden size
- Instruction-conditioned via AdaptiveRMSNorm (FiLM)
- Sinusoidal time embedding for flow matching
- ~64M trainable parameters
- Action Space: 6 steps x 20 dims (4 sticks + 16 buttons per step)
- Training: Flow matching with Euler ODE integration at inference
Files
action_decoder.pt— Trained action decoder weightsdecoder_config.json— Architecture and tokenizer configtokenizer.json/tokenizer_config.json— Tokenizer with special tokenschat_template.jinja— Chat templateprocessor_config.json— Processor config
- License
- apache-2.0
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026