Qwen3.5-4B · Pareto Curriculum SFT
This is the best checkpoint from a three-stage Pareto curriculum SFT run on Qwen3.5-4B. It was trained with ordinary unweighted token cross-entropy and without Error Tool-Call Mask.
Training summary
- Base model:
Qwen/Qwen3.5-4B - Selected checkpoint: Stage 3, global step 105
- Training data: Qwen3.5-122B distilled trajectories with reward >= 0.3
- Curriculum: reward 0.3-0.5 -> case-wise Pareto 0.3-0.7 -> highest band per case 0.3-1.0
- Loss: unweighted assistant-token cross-entropy
- Error Tool-Call Mask: disabled
Custom chat template
The repository includes chat_template.jinja, a custom Qwen3.5 template used
for both SFT rendering and inference. Unlike the stock history behavior, it
always replays non-empty assistant reasoning_content inside <think> blocks.
It also renders parallel tool calls with the XML-style Qwen tool-call format and
groups tool responses into the following user turn.
AutoProcessor.from_pretrained() loads the bundled template. When serving with
SGLang, pass it explicitly to ensure training/inference parity:
python -m sglang.launch_server \
--model-path /path/to/model \
--chat-template /path/to/model/chat_template.jinja \
--reasoning-parser qwen3 \
--tool-call-parser qwen3_coder
Thinking is enabled by default. To render a generation prompt without an open
reasoning block, pass enable_thinking=False in the chat-template kwargs.
Transformers loading
import torch
from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
model_id = "/path/to/model"
processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3_5ForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
text = processor.apply_chat_template(
[{"role": "user", "content": "Describe the video."}],
tokenize=False,
add_generation_prompt=True,
enable_thinking=True,
)
The checkpoint is stored as Hugging Face safetensors. Optimizer, scheduler, trainer, and RNG states are intentionally excluded.