reaperdoesntknow / Qemma-sft

Model Card for Qemma

Qemma is a HuggingFace-native hybrid model that merges Gemma-3 (1B) and Qwen-3 (0.6B) at the weight level (no adapters). Design: Gemma MLP/body + Qwen attention/head, projected and aligned to Gemma’s hidden size. The model is then SFT-tuned for stepwise reasoning.

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "reaperdoesntknow/Qemma-sft"
tok = AutoTokenizer.from_pretrained(model_id, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).eval()

messages = [{"role": "user", "content": "Explain finite-scale discrepancy Δ_r in one paragraph."}]
inputs = tok.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

out = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9)
print(tok.decode(out[0], skip_special_tokens=True))

What’s inside

• Architecture: Gemma-3 backbone (26 layers, hidden 1152, MLP 6912) with Qwen-style attention regrouped to Gemma’s 4×256 heads.
• Tokenizer: Gemma-3 tokenizer and chat template (see chat_template.jinja ).
• Training: SFT for instruction following and stepwise reasoning.

Intended use & limitations

Use: research, instruction following, code/help, analysis, further SFT/RLHF. Limits: may hallucinate; not for safety-critical, medical, legal, or financial decisions. Follow dataset/model licenses.

Training procedure

• ~512 warm-start steps (Alpaca-style data)
• 256 Additional pretraining steps on (O1-OPEN/OpenO1-SFT)
• 128 SFT steps with (Jackrong/gpt-oss-120b-reasoning-STEM-5K)
• 256 SFT steps with (O1-OPEN/OpenO1-SFT)

Framework versions

• TRL: 0.25.0
• Transformers: 4.57.1
• Pytorch: 2.8.0+cpu
• Datasets: 4.4.1
• Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}