Upload folder using huggingface_hub

README.md

@@ -71,7 +71,7 @@ model-index:
 **A 48M-parameter tool-calling model that beats [Needle 2](https://cactuscompute.com/needle)
 on 3 of its 5 published benchmarks — including the one it's named after — with 150× less training data.**
 
-[**GitHub (code, evals, full experimental record)**](https://github.com/nikshepsvn/tiny-toolcall) · MIT · 48.12M params · 11.5MB at 2-bit · $260 total build cost
+[**GitHub (code, evals, full experimental record)**](https://github.com/nikshepsvn/thimble) · MIT · 48.12M params · 11.5MB at 2-bit · $260 total build cost
 
 ![Results](results.png)
 
@@ -94,7 +94,7 @@ Two things to know before quoting the table: the Seal-in margin (+0.5 on 700
 rows) is within sampling noise and we say so, and the pre-registered model
 selector actually picked a sibling checkpoint that scored worse — the failure is
 diagnosed, both models' results are published, and the full story is in
-[RESULTS.md](https://github.com/nikshepsvn/tiny-toolcall/blob/master/RESULTS.md).
+[RESULTS.md](https://github.com/nikshepsvn/thimble/blob/master/RESULTS.md).
 
 ## Why a thimble beats a needle
 
@@ -153,8 +153,8 @@ The most reusable part of the project. Each idea was killed by an A/B, not an ar
 The guarantees live in the decoding harness, so inference goes through the repo:
 
 ```bash
-git clone https://github.com/nikshepsvn/tiny-toolcall
-cd tiny-toolcall && uv venv && uv pip install -e .
+git clone https://github.com/nikshepsvn/thimble
+cd thimble && uv venv && uv pip install -e .
 # put thimble-v6.pt in checkpoints/, tokenizer.json in data/
 python scripts/final_eval.py --ckpt thimble-v6 --suite seal-tools-in
 ```