Upload README.md with huggingface_hub

README.md

@@ -1,26 +1,64 @@
----
-tags:
-- ml-intern
----
+# FinJEPA: Financial Joint-Embedding Predictive Architecture
 
-# ashesh8500/finjepa
+FinJEPA is a JEPA-based world model for portfolio optimization over a **separated action space** consisting of:
+- **Portfolio weights** (continuous, simplex-constrained)
+- **Trading signals** (discrete: long/short/flat per asset)
+- **Hedging signal** (binary: on/off)
 
-<!-- ml-intern-provenance -->
-## Generated by ML Intern
+## Architecture (SOTA Blend)
 
-This model repository was generated by [ML Intern](https://github.com/huggingface/ml-intern), an agent for machine learning research and development on the Hugging Face Hub.
+| Component | Source | Key Innovation |
+|-----------|--------|----------------|
+| Time Series Encoder | TS-JEPA (Sennadir 2025) | 1D-CNN patch tokenizer + Transformer |
+| Action Conditioning | JEPA-WMs (Terver 2025) | AdaLN + RoPE in predictor |
+| Collapse Prevention | EB-JEPA (Terver 2026) | SIGReg + Inverse Dynamics Model |
+| Multi-step Rollout | EB-JEPA | K-step autoregressive training |
+| Planner | JEPA-WMs + EB-JEPA | CEM L2 cost / MPPI cumulative cost in latent space |
+| TD Branch | TD-JEPA (Bagatella 2025) | Optional separate task encoder for zero-shot RL |
 
-- Try ML Intern: https://smolagents-ml-intern.hf.space
-- Source code: https://github.com/huggingface/ml-intern
+## Model
+
+```
+Financial Time Series (T, F)
+    │
+    ▼
+[TimeSeriesTokenizer] ── 1D-CNN patches + position encoding
+    │
+    ├───► [Context Encoder] (student)
+    │          │
+    │          ▼
+    │     [Predictor] ◄─── Action embedding (weights + signals)
+    │     (AdaLN + RoPE)       │
+    │          │               │
+    │          ▼               ▼
+    │     Predicted target  [ActionEmbedder]
+    │     embeddings           ├── weights (continuous)
+    │                            ├── signals (discrete)
+    │                            └── hedge (binary)
+    │
+    └───► [Target Encoder] (teacher, EMA frozen)
+              │
+              ▼
+         Ground truth target embeddings
+```
 
 ## Usage
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+```bash
+python finjepa/run_training_fast.py
+```
 
-model_id = "ashesh8500/finjepa"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+Full training on real data:
+```bash
+python finjepa/train.py --data_source hf \
+  --dataset_name paperswithbacktest/Stocks-Daily-Price \
+  --n_assets 5 --batch_size 128 --epochs 50 --push_to_hub
 ```
 
-For non-causal architectures, replace `AutoModelForCausalLM` with the appropriate `AutoModel` class.
+## References
+
+1. TS-JEPA — Sennadir et al. (2025). arxiv:2509.25449
+2. JEPA-WMs — Terver et al. (2025). arxiv:2512.24497
+3. EB-JEPA — Terver et al. (2026). arxiv:2602.03604
+4. V-JEPA 2 — Assran et al. (2025). arxiv:2506.09985
+5. TD-JEPA — Bagatella et al. (2025). arxiv:2510.00739