group_model

Model details

• Base model: Qwen/Qwen3-1.7B
• Post-training: SFT (LoRA adapter, merged back into the base weights), then GRPO seeded from the SFT checkpoint with reward functions for the math and reasoning objectives
• Domains: math (free-form, pass@8) and general knowledge, safety, multilinguality (multiple-choice, pass@1)
• Format: vLLM-loadable safetensors with config.json, generation_config.json, and a tokenizer chat_template

Output contract

The model writes its reasoning and then wraps the final answer in \boxed{...}. The training mix covers both question styles, because the group model is scored on both:

Free-form:

markdown
Copy code
Q: What is the smallest prime greater than 100?
A: ...reasoning... \boxed{101}

Multiple-choice (the boxed content is the option letter, with 2 to 20 options):

markdown
Copy code
Q: Which of the following is a noble gas?
A) Oxygen
B) Argon
C) Nitrogen
D) Hydrogen
A: ...reasoning... \boxed{B}

Thinking mode

This model runs in thinking mode: it emits a <think>...</think> reasoning block before the final \boxed{...} answer. Thinking is forced on inside the chat template, because the evaluation passes only tokenizer.apply_chat_template(messages, add_generation_prompt=True) with no enable_thinking argument, so the template default is the only signal honored.

The relevant line in chat_template.jinja:

jinja
Copy code
{%- set enable_thinking = true %}

Usage

python
Copy code
from transformers import AutoTokenizer, AutoModelForCausalLM

tok = AutoTokenizer.from_pretrained("cs-552-2026-aaty/group_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-aaty/group_model")

messages = [{"role": "user", "content": "What is the capital of Australia?"}]
prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(tok.decode(out[0], skip_special_tokens=True))

Training data

• SFT: cs-552-2026-aaty/sft_mixture, the chat-formatted mixture built from public QA, knowledge, instruction, and math datasets.
• GRPO: cs-552-2026-aaty/grpo_mixture, prompts with verifiable answers used for reward-driven optimization.

See the team data pipeline in code/data/ for the exact sources and filters.