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

Discrepancy Calculus Foundation

This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces.

DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as structural signals that reveal the geometry of the learning problem. Key concepts:

• Discrepancy Operator (D): Measures the gap between expected and observed behavior at each training step
• Jump Sets: Boundaries where model behavior changes discontinuously — these are features, not bugs
• Ghost Imprinting: Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal

For the full mathematical treatment, see Discrepancy Calculus: Foundations and Core Theory (DOI: 10.57967/hf/8194).

Citation chain: Structure Over Scale (DOI: 10.57967/hf/8165) → Three Teachers to Dual Cognition (DOI: 10.57967/hf/8184) → Discrepancy Calculus (DOI: 10.57967/hf/8194)

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}}
}

---

Convergent Intelligence Portfolio

By Convergent Intelligence LLC: Research Division

Top Models from Our Lab

Total Portfolio: 41 models | 2,781 total downloads

Last updated: 2026-03-28 12:57 UTC

<!-- CIX-CROSSLINK-START -->

---

From the Convergent Intelligence Portfolio

DistilQwen Collection — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware.

Top model: Qwen3-1.7B-Coder-Distilled-SFT — 508 downloads

Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165)

Convergent Intelligence LLC: Research Division

<!-- CIX-CROSSLINK-END --> <!-- cix-keeper-ts:2026-09-29T13:16:17Z -->