Card: repository renamed

README.md

@@ -14,18 +14,18 @@ datasets:
 - ThinkMorph/Pretext-270K
 ---
 
-# ThinkMorph-SSL-Stage1
+# ThinkMorph-SSL
 
 This is the **intermediate Stage 1 model** of the PRIMER recipe. It is the EMA weights at
 step 5,500 of the pretext stage, trained from BAGEL-7B-MoT on
 [Pretext-270K](https://huggingface.co/datasets/ThinkMorph/Pretext-270K). The final model,
-[ThinkMorph-SSL](https://huggingface.co/ThinkMorph/ThinkMorph-SSL), starts its Stage 2 training from these weights.
+[ThinkMorph-SSL-Instruct](https://huggingface.co/ThinkMorph/ThinkMorph-SSL-Instruct), starts its Stage 2 training from these weights.
 
 > **This model has only had pretext training, with no question-answer supervision.** Its
 > exercises take a corrupted input image and output a description, a restored image and a
 > second description. It is not meant to answer questions directly. The paper's appendix
 > reports roughly 40% on V\* and MMMU for this checkpoint. For question answering, use
-> ThinkMorph-SSL.
+> ThinkMorph-SSL-Instruct.
 
 ## Files
 
@@ -43,9 +43,9 @@ step 5,500 of the pretext stage, trained from BAGEL-7B-MoT on
 | `special_tokens_map.json` | 613 | `76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd` |
 | `tokenizer_config.json` | 4,864 | `b7af0d4c9b917db05150006b466cfa2e8424b3915ff5fe2023a6f512a5e16dd5` |
 
-All files except `ema.safetensors` are byte-identical to the ThinkMorph-SSL release. The
-checkpoint's own config and tokenizer files were compared with those of ThinkMorph-SSL and
-are the same. `ema.safetensors` uses the same format as ThinkMorph-SSL: 1,451 bfloat16 tensors
+All files except `ema.safetensors` are byte-identical to the ThinkMorph-SSL-Instruct release. The
+checkpoint's own config and tokenizer files were compared with those of ThinkMorph-SSL-Instruct and
+are the same. `ema.safetensors` uses the same format as ThinkMorph-SSL-Instruct: 1,451 bfloat16 tensors
 with the same names and shapes. The unused 26th SigLIP layer is left out.
 
 ## How the file was made
@@ -56,9 +56,9 @@ with the same names and shapes. The unused 26th SigLIP layer is left out.
 2. `scripts/merge_checkpoint.py --checkpoint-type ema` from the PRIMER code release merged
    the EMA state into a single fp32 `model.safetensors`. All 1,467 weights came from the EMA
    state; none were filled in from a base model.
-3. The 1,451 tensors that ThinkMorph-SSL ships were cast once to bfloat16, with no other
+3. The 1,451 tensors that ThinkMorph-SSL-Instruct ships were cast once to bfloat16, with no other
    change, and saved as `ema.safetensors`. A spot check confirmed that the cast values match
-   exactly. The VAE weights are identical to ThinkMorph-SSL's, as expected, because the VAE
+   exactly. The VAE weights are identical to ThinkMorph-SSL-Instruct's, as expected, because the VAE
    is frozen in both stages.
 
 ## Training
@@ -76,7 +76,7 @@ with the same names and shapes. The unused 26th SigLIP layer is left out.
 
 ## Loading
 
-Loading works the same way as for ThinkMorph-SSL. With the official BAGEL inference code or
+Loading works the same way as for ThinkMorph-SSL-Instruct. With the official BAGEL inference code or
 the PRIMER code release, point `model_path` at a local copy. The loader reads
 `ema.safetensors`.