Update model card for public weights release

README.md

@@ -20,8 +20,6 @@ Sol Pro is a **138,037,594-parameter** language model from Sol Labs. It combines
 
 The released checkpoint scores **29.37 on the normalized Intelligence Index** and **24.01 on the raw accuracy Index**.
 
-The final weights are saved in the private checkpoint bucket. Their upload to this repository is pending because the organization has reached its private storage limit. The loading example below becomes available once the weights upload completes.
-
 ## Model
 
 | Setting | Value |
@@ -43,11 +41,10 @@ Four middle blocks run twice. Causal grouped-query attention uses learned Q/K RM
 
 ## Load and generate
 
-Install the dependencies and authenticate with an account that can access this private repository:
+Install the dependencies:
 
 ```bash
 pip install torch safetensors tokenizers huggingface_hub
-hf auth login
 ```
 
 ```python
@@ -102,7 +99,6 @@ Sol Pro supports text-completion and small-model research. Multiple-choice score
 | File | Contents |
 |---|---|
 | `model.safetensors` | Released inference weights |
-| `checkpoint.pt` | Complete final checkpoint, including optimizer state; upload pending |
 | `modeling_sol_pro.py` | Architecture, loader, and text generator |
 | `config.json` | Architecture configuration |
 | `tokenizer.json` | Original tokenizer |