| --- |
| license: apache-2.0 |
| datasets: |
| - Jclennon/TableMind-data |
| language: |
| - en |
| metrics: |
| - exact_match |
| - accuracy |
| base_model: |
| - Qwen/Qwen3-8B |
| --- |
| # TableMind Reinforced Model Weights |
|
|
| These are the official **reinforcement learning (RL) fine-tuned model checkpoints** for the paper: |
| **"TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning"**. |
|
|
| --- |
| ## 📦 Model Details |
|
|
| * **Base Model**: Qwen3-8B |
| * **Tuning Framework**: [Verl](https://github.com/volcengine/verl) + [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory) |
|
|
| This model follows the standard Hugging Face `transformers` format and uses the efficient `safetensors` backend. |
|
|
| ``` |
| Time-R1/ |
| ├── added_tokens.json |
| ├── config.json |
| ├── generation_config.json |
| ├── merges.txt |
| ├── model-00001-of-00004.safetensors |
| ├── model-00002-of-00004.safetensors |
| ├── model-00003-of-00004.safetensors |
| ├── model-00004-of-00004.safetensors |
| ├── model.safetensors.index.json |
| ├── special_tokens_map.json |
| ├── tokenizer.json |
| ├── tokenizer_config.json |
| └── vocab.json |
| ``` |
|
|
| --- |
