Fix generation from the published artifact; rewrite model card

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/bear.jpg filter=lfs diff=lfs merge=lfs -text
+examples/bus.jpg filter=lfs diff=lfs merge=lfs -text
+examples/cats.jpg filter=lfs diff=lfs merge=lfs -text
+examples/stop.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -25,22 +25,20 @@ Model in the **sub-1B parameter** class. It extends
 [PleIAs/Baguettotron](https://huggingface.co/PleIAs/Baguettotron) — a 321M
 text-only reasoning SLM — with visual capabilities via the
 [InternViT-300M-448px-V2.5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5)
-vision encoder and a lightweight MLP projector, for a total of ~628M parameters.
-
-It inherits six European languages (EN, FR, DE, ES, IT, PL) from the Baguettotron
-backbone, and — unusually — its entire LM pretraining corpus is auditable: Baguettotron
-was trained on [SYNTH](https://huggingface.co/datasets/PleIAs/SYNTH), ~58K Wikipedia
-articles expanded synthetically, with no scraped web.
+vision encoder and a lightweight MLP projector, for a total of ~628M parameters. It
+inherits six European languages (EN, FR, DE, ES, IT, PL) from the Baguettotron backbone.
 
 Two checkpoints are published:
 
-- [**baguettotron-vision-vqa**](https://huggingface.co/andreagemelli/baguettotron-vision-vqa)
-  — instruction-tuned on The Cauldron. **This is the model you want.**
 - [baguettotron-internvit-alignment](https://huggingface.co/andreagemelli/baguettotron-internvit-alignment)
-  — projector-only warmup, published so the alignment stage can be reproduced.
+  — the projector-only warmup. It describes images, and nothing more.
+- [baguettotron-vision-vqa](https://huggingface.co/andreagemelli/baguettotron-vision-vqa)
+  — instruction-tuned on top of it. It goes past plain description and follows visual
+  instructions, so prefer it for a richer chat experience.
 
-Apache 2.0. This is a proof of concept and a costed recipe, not a SOTA attempt.
-Source: [github.com/andreagemelli/baguettotron-vlm](https://github.com/andreagemelli/baguettotron-vlm).
+Apache 2.0.
+Source: [github.com/andreagemelli/baguettotron-vlm](https://github.com/andreagemelli/baguettotron-vlm) ·
+Write-up: [andreagemelli.me/posts/baguettotron-vlm](https://andreagemelli.me/posts/baguettotron-vlm/)
 
 
 > **Alignment checkpoint.** Only the MLP projector was trained (on LLaVA-CC3M-Pretrain-595K) — the ViT and the Baguettotron LLM are unmodified base weights. It writes short captions and nothing more. Published so the alignment stage can be reproduced; for actual use take [baguettotron-vision-vqa](https://huggingface.co/andreagemelli/baguettotron-vision-vqa).
@@ -92,43 +90,25 @@ print(model.chat(**inputs))
 
 ### Example output
 
-Greedy, prompt `Describe the image concisely.` — verbatim output:
+Greedy, prompt `Describe the image concisely.` — verbatim output. Images from [COCO](https://cocodataset.org) val2017.
 
 | | output |
 |---|---|
-| <img src="http://images.cocodataset.org/val2017/000000039769.jpg" width="180"> | `a cat is sleeping on the couch` |
-| <img src="http://images.cocodataset.org/val2017/000000000285.jpg" width="180"> | `the bear is a good friend.` |
-| <img src="http://images.cocodataset.org/val2017/000000000724.jpg" width="180"> | `a sign for a stop sign` |
-| <img src="http://images.cocodataset.org/val2017/000000001584.jpg" width="180"> | `the bus is a red double - decoration` |
-
-That is the honest range of this checkpoint: it locates the subject and then drifts, which is what 2.7M trained parameters buys. It does not read the text on the sign or the bus.
+| <img src="examples/cats.jpg" width="180"> | `a cat is sleeping on the couch` |
+| <img src="examples/bear.jpg" width="180"> | `the bear is a good friend.` |
+| <img src="examples/stop.jpg" width="180"> | `a sign for a stop sign` |
+| <img src="examples/bus.jpg" width="180"> | `the bus is a red double - decoration` |
 
 ### Chat template
 
 Trained on short image captions with no `<think>` traces. The processor emits a bare assistant prefix (`<|im_start|>assistant\n`) and the model completes the caption directly. Keep prompts simple ("Describe the image").
 
-## Recommended settings
-
-Greedy decoding, which is what `chat()` does by default — just call it. Four decoding
-presets were compared on held-out images and the differences sat inside noise, so greedy
-is preferred for being deterministic rather than for scoring better.
-
-Two things that *do* move the needle:
-
-- **Ask specific questions.** `"How many cats are there?"` answers `2.`; the vaguer
-  `"What is in the picture?"` answers `Yes.` Phrasing matters far more at this scale
-  than it does with a large model.
-- **Describe first, then ask.** A follow-up question in a second turn is answered better
-  than the same question asked cold, because the model conditions on its own previous
-  answer. Multi-turn is in-distribution — The Cauldron contains multi-turn conversations.
-
 ## Limitations
 
 - **Resolution ceiling.** One 448×448 crop → 256 visual tokens puts document text at
   roughly 2–4 px/char. OCR, charts and documents are out of reach by architecture, not
   by budget. Neither published checkpoint reads text in an image.
 - **Hallucinations**, especially on fine-grained or text-heavy questions.
-- **Undertrained for VQA alignment** relative to the size of the data mixture.
 - **Multilingual capability is inherited, not verified.** The backbone covers six
   languages; the VLM was never evaluated on non-English benchmarks.