Add ToolWeave Stage 1 model card and branding

README.md

@@ -0,0 +1,38 @@
+<div align="center">
+
+<img src="assets/toolweave-mark.svg" alt="ToolWeave mark" width="110">
+
+# ToolWeave Stage 1
+
+**Tool-use cold-start checkpoint for multi-turn tool-calling agents.**
+
+</div>
+
+## Model summary
+
+ToolWeave Stage 1 is the first curriculum checkpoint in the ToolWeave project. It is trained to improve parser-compatible tool-call formatting, executable interaction, and stable multi-turn tool-use behavior in the BFCL environment.
+
+- Base family: Qwen3-4B-Instruct
+- Curriculum stage: Stage 1 — Tool-Use Cold Start
+- Checkpoint: selected Stage 1 update 25
+- Training signal: format and executable tool-use feedback
+
+This repository contains the Stage 1 checkpoint. It is not the final ToolWeave model.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "muradil211/ToolWeave_stage1"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+```
+
+Tool-use inference requires the model's function schemas and the Qwen3-compatible tool-call format.
+
+## Links
+
+- [ToolWeave project](https://github.com/Muradil-mamat-211/ToolWeave)
+- [BFCL](https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard)
+