grpo-tournament-qwen is an open-weight model from Siddharth Doshi. Its published files total 89.8 MB.
This model is a fine-tuned version of unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Model Card
This model is a fine-tuned version of unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Excerpt from the card by Siddharth Doshi.
Identity and Version
- Repository
- Siddhuuuu/grpo-tournament-qwen
- Publisher
- Siddharth Doshi
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- trl
- Revision
- b0a714fda5c5e0985d872e5e0e7d71cd5e8edcc3
- First published
- 2026-09-21
- Last updated
- 2026-09-22
Files and Weights
12 files, 89.8 MB in total. The weights are 2 files totalling 73.9 MB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 73.9 MB | e67126ad7baa |
| training_args.bin | Weights | 7.4 KB | b9f4a3e8af73 |
| adapter_config.json | Configuration | 1.3 KB | — |
| added_tokens.json | Configuration | 605 B | — |
| special_tokens_map.json | Configuration | 614 B | — |
| README.md | Documentation | 2.1 KB | — |
| chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 9c5ae00e602b |
| tokenizer_config.json | Tokenizer | 4.7 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 73.9 MB
Released by Siddharth Doshi through its official repository on Hugging Face.
Built From
- Described by arXiv:2402.03300
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 73.9 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.