Upload README.md with huggingface_hub

README.md

@@ -20,11 +20,20 @@ Ivan Lee, Cheng Yang, Taylor Berg-Kirkpatrick
 
 ## Available Checkpoints
 
-| Checkpoint | Objective | Hybrid | Training | PPL |
-|------------|-----------|--------|----------|-----|
-| `vision_base_h0_recon` | Reconstruction | 0 | - | 1.03 |
-| `vision_base_h0_lm` | LM | 0 | Direct | 5.08 |
-| `vision_base_h0_lm_recon-init` | LM | 0 | From reconstruction | 5.06 |
+### Vision (base, 768x768)
+
+| Checkpoint | Objective | Hybrid | Training | CR | PPL |
+|------------|-----------|--------|----------|-----|-----|
+| `vision_base_h0_recon` | Reconstruction | 0 | - | 3.60 | 1.03 |
+| `vision_base_h0_lm` | LM | 0 | Direct | 3.60 | 5.08 |
+| `vision_base_h0_lm_recon-init` | LM | 0 | From recon | 3.60 | 5.06 |
+
+### Meanpool (w4s4)
+
+| Checkpoint | Objective | Hybrid | Training | CR | PPL |
+|------------|-----------|--------|----------|-----|-----|
+| `meanpool_w4s4_h0_recon` | Reconstruction | 0 | - | 3.97 | 1.04 |
+| `meanpool_w4s4_h0_lm_recon-init` | LM | 0 | From recon | 3.97 | 5.02 |
 
 ## Naming Convention
 
@@ -35,15 +44,14 @@ Ivan Lee, Cheng Yang, Taylor Berg-Kirkpatrick
 | Field | Values | Description |
 |-------|--------|-------------|
 | regime | vision, conv1d, meanpool, text | Compression architecture |
-| config | base/small/tiny/large, t500/t250, w10s10, ctx525 | Regime-specific config |
-| h{N} | h0, h100 | Hybrid text tokens (0 = pure vision) |
+| config | base/small/tiny/large, t500/t250, w4s4/w10s10, ctx525 | Regime-specific config |
+| h{N} | h0, h100 | Hybrid text tokens (0 = pure vision/compression) |
 | objective | recon, lm | Training objective |
 | recon-init | (optional) | LM initialized from reconstruction checkpoint |
 
 ## Model Details
 
 - **Architecture**: DeepSeek-OCR with trainable vision encoder
-- **Image Size**: 768x768 (base)
 - **Encoder Status**: Trained (not frozen)
 - **Dataset**: 510k samples from FineWiki