mdonigian/trellis-sft

Trellis-506M-SFT

Supervised fine-tuned version of Trellis-506M, a 506M parameter LLaMA-style language model optimized for structured output tasks — JSON generation, function calling, schema compliance, and structured extraction.

Model Details

SFT Training

Dataset

Trained on mdonigian/full-structured-instruction-sft-dataset (~95k examples), assembled from:

All examples are standardized to a common chat format using custom special tokens (see below). Source-specific filtering includes deduplication, token length capping (2048), and quality validation.

Hyperparameters

Training Details

• —Framework: TRL SFTTrainer
• —Attention: Flash Attention 2
• —Compilation: torch.compile enabled
• —Loss masking: Completion-only — loss computed only on assistant response tokens, not system/user/tool tokens
• —Hardware: NVIDIA B200

Chat Format

All training data uses these special tokens:

<|system|>You are a helpful assistant that generates valid JSON.<|end|>
<|user|>Generate a user profile with name, email, and age.<|end|>
<|assistant|>{"name": "Alice Chen", "email": "alice@example.com", "age": 28}<|end|>

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "mdonigian/trellis-sft",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("mdonigian/trellis-sft")

prompt = """<|system|>You are a helpful assistant that generates valid JSON.<|end|>
<|user|>Generate a JSON object for a book with title, author, year, and genre.<|end|>
<|assistant|>"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=False))

Experimental Design

This model is one component of a controlled experiment comparing curated pretraining vs. standard pretraining for structured output tasks:

All three models undergo identical SFT with the same dataset, hyperparameters, and training procedure. Post-SFT evaluation covers:

• —Tier 1: Custom structured output benchmarks (JSON schema compliance, structured extraction, classification)
• —Tier 2: General NLP benchmarks via lm_eval (HellaSwag, ARC, PIQA, Winogrande, MMLU)
• —Tier 3: Code benchmarks (HumanEval, MBPP)

Limitations

• —506M parameters limits general knowledge and complex reasoning
• —Context length capped at 2,048 tokens
• —No safety training, RLHF, or DPO alignment
• —Optimized for structured output; general chat quality is limited

Citation

@misc{trellis-sft-2026,
  title={Trellis-506M-SFT: Supervised Fine-Tuning for Structured Output},
  author={Donigian, Matt},
  year={2026},
  url={https://huggingface.co/mdonigian/trellis-sft}
}