Update README.md

README.md

@@ -24,20 +24,19 @@ datasets:
 
 **TinyFlux-Lailah** is an expanded TinyFlux architecture with increased depth and width. Originally ported from [TinyFlux](https://huggingface.co/AbstractPhil/tiny-flux) with strategic layer expansion and attention head doubling, now training end-to-end on teacher latents.
 
-> **Current checkpoint:** `step_286250` | **Status:** Active training
 
 ## Quick Start (Colab)
 
 The easiest way to test Lailah:
 
 1. Open [Google Colab](https://colab.research.google.com/)
-2. Copy the contents of [`colab_inference_lailah_early.py`](./colab_inference_lailah_early.py) 
+2. Copy the contents of [`inference_v3.py`](./inference_v3.py) 
 3. Run the cells
 
 ```python
 # Or fetch directly:
-!wget https://huggingface.co/AbstractPhil/tiny-flux-deep/raw/main/colab_inference_lailah_early.py
-%run colab_inference_lailah_early.py
+!wget https://huggingface.co/AbstractPhil/tiny-flux-deep/raw/main/inference_v3.py
+%run inference_v3.py
 ```
 
 ## Fair Weights
@@ -93,9 +92,9 @@ Training on [AbstractPhil/flux-schnell-teacher-latents](https://huggingface.co/d
 
 ### Checkpoints
 
-Checkpoints are saved every 625 steps with both main and EMA weights:
+Checkpoints are saved every epoch or so with both main and EMA weights:
 - `checkpoints/step_XXXXX.safetensors` - Training weights
-- `checkpoints/step_XXXXX_ema.safetensors` - EMA weights (recommended for inference)
+- `checkpoints/step_XXXXX_ema.safetensors` - EMA weights (currently very broken and retraining, use standard step to inference)
 
 ## Usage
 
@@ -116,10 +115,10 @@ from safetensors.torch import load_file
 config = TinyFluxDeepConfig()
 model = TinyFluxDeep(config).to("cuda", torch.bfloat16)
 
-# Load EMA weights (recommended) or main weights
+# Load EMA weights (broken) or main weights
 weights = load_file(hf_hub_download(
     "AbstractPhil/tiny-flux-deep", 
-    "checkpoints/step_286250_ema.safetensors"  # Use _ema for best quality
+    "checkpoints/step_286250_ema.safetensors"  # EMA will be better later, for now it's broken.
 ))
 model.load_state_dict(weights, strict=False)
 model.eval()
@@ -174,7 +173,7 @@ AbstractPhil/tiny-flux-deep/
 ├── train_tinyflux_deep.py         # Training script
 ├── checkpoints/
 │   ├── step_286250.safetensors    # Training weights
-│   └── step_286250_ema.safetensors # EMA weights (use this)
+│   └── step_286250_ema.safetensors # EMA weights (currently broken)
 ├── samples/                        # Generated samples during training
 └── README.md
 ```
@@ -240,4 +239,4 @@ MIT License
 
 ---
 
-**Status**: Active training. Checkpoints updated regularly. Use EMA weights for best results.
+**Status**: Active training. Checkpoints updated regularly. Use standard weights for best results.