82 lines
2.7 KiB
Markdown
82 lines
2.7 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model: Qwen/Qwen3-4B-Instruct-2507
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- spade
|
|
- self-play
|
|
- reinforcement-learning
|
|
- environment-generation
|
|
- games
|
|
---
|
|
|
|
# SPADE-Qwen3-4B-Games
|
|
|
|
SPADE checkpoint for the **games** setting, trained from [`Qwen/Qwen3-4B-Instruct-2507`](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
|
|
|
SPADE trains a single model in two roles: an **Environment Designer** that writes executable
|
|
environments, and a **Reasoning Agent** that solves them. The Designer is rewarded for
|
|
producing environments at the frontier of what the Agent can currently solve, so
|
|
the curriculum keeps pace with the policy instead of being fixed in advance.
|
|
See the [paper](https://arxiv.org/abs/2608.19197) for details.
|
|
|
|
| | |
|
|
|---|---|
|
|
| Base model | [`Qwen/Qwen3-4B-Instruct-2507`](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) |
|
|
| Setting | games |
|
|
| Context length | 262,144 |
|
|
|
|
## Quickstart
|
|
|
|
We advise you to use the latest version of `transformers`.
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_name = "spade-rl/SPADE-Qwen3-4B-Games"
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_name,
|
|
torch_dtype="auto",
|
|
device_map="auto"
|
|
)
|
|
|
|
prompt = "Give me a short introduction to large language model."
|
|
messages = [{"role": "user", "content": prompt}]
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|
|
|
generated_ids = model.generate(**model_inputs, max_new_tokens=16384)
|
|
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
|
print(tokenizer.decode(output_ids, skip_special_tokens=True))
|
|
```
|
|
|
|
## Deployment
|
|
|
|
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` to create an
|
|
OpenAI-compatible API endpoint:
|
|
|
|
- SGLang:
|
|
```shell
|
|
python -m sglang.launch_server --model-path spade-rl/SPADE-Qwen3-4B-Games --context-length 262144
|
|
```
|
|
- vLLM:
|
|
```shell
|
|
vllm serve spade-rl/SPADE-Qwen3-4B-Games --max-model-len 262144
|
|
```
|
|
|
|
Note: If you encounter out-of-memory (OOM) issues, consider reducing the context
|
|
length to a shorter value, such as 32,768.
|
|
|
|
## Best practices
|
|
|
|
We recommend `temperature=0.7`, `top_p=0.8`, `top_k=20`, `min_p=0`, following
|
|
the sampling guidance on the [base model card](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
|
|
|
## Related artifacts
|
|
|
|
- Grounding corpora: [games](https://huggingface.co/datasets/spade-rl/spade-grounding-corpus-games-15k) | [tool use](https://huggingface.co/datasets/spade-rl/spade-grounding-corpus-tooluse-15k)
|
|
- All SPADE models, data and generated environments: [huggingface.co/spade-rl](https://huggingface.co/spade-rl)
|