Model Card for Qemma

Redux This Model underwent an additional merge between Qemma-sft and Qwen3-0.6B, in addition to adding Rope Scaling. 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. This variant uses Yarn based Rope Scaling with 1:1 Ratio from max_position_embeddings

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

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

text = "I notice that the sum involves the absolute values of three linear expressions of x."
inputs = tokenizer(text, return_tensors="pt", max_length=64, padding='max_length', truncation=True)
inputs = {k: v.to(model.device) for k, v in inputs.items()}

with torch.no_grad():
    model.eval()
    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, min_length=32)
print(tokenizer.decode(outputs[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}}
}