Instructions to use reaperdoesntknow/Qemma-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reaperdoesntknow/Qemma-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="reaperdoesntknow/Qemma-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reaperdoesntknow/Qemma-sft")
model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/Qemma-sft", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reaperdoesntknow/Qemma-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reaperdoesntknow/Qemma-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reaperdoesntknow/Qemma-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/reaperdoesntknow/Qemma-sft

SGLang

How to use reaperdoesntknow/Qemma-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "reaperdoesntknow/Qemma-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reaperdoesntknow/Qemma-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "reaperdoesntknow/Qemma-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reaperdoesntknow/Qemma-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use reaperdoesntknow/Qemma-sft with Docker Model Runner:
```
docker model run hf.co/reaperdoesntknow/Qemma-sft
```

Qemma-sft / README.md

reaperdoesntknow

keeper: refresh 2026-05-21

ea56090 verified 3 months ago

preview code

Raw

History Blame

6.02 kB

	---
	library_name: transformers
	model_name: Qemma-sft
	tags:
	- generated_from_trainer
	- sft
	- trl
	- convergentintel
	licence: license
	license: osl-3.0
	datasets:
	- O1-OPEN/OpenO1-SFT
	- yahma/alpaca-cleaned
	- Jackrong/gpt-oss-120b-reasoning-STEM-5K
	language:
	- en
	base_model:
	- google/gemma-3-1b-it
	- Qwen/Qwen3-0.6B
	pipeline_tag: text-generation
	---

	# 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

	```python
	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](https://huggingface.co/reaperdoesntknow) 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](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194).

	Citation chain: [Structure Over Scale](https://huggingface.co/reaperdoesntknow/Structure-Over-Scale) (DOI: 10.57967/hf/8165) → [Three Teachers to Dual Cognition](https://huggingface.co/reaperdoesntknow/DualMind_Methodolgy) (DOI: 10.57967/hf/8184) → [Discrepancy Calculus](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194)

	## Citations



	Cite TRL as:

	```bibtex
	@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](https://huggingface.co/reaperdoesntknow)


	### Top Models from Our Lab

	\| Model \| Downloads \|
	\|-------\|-----------\|
	\| [Qwen3-1.7B-Thinking-Distil](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Thinking-Distil) \| 501 \|
	\| [LFM2.5-1.2B-Distilled-SFT](https://huggingface.co/reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT) \| 342 \|
	\| [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) \| 302 \|
	\| [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF) \| 203 \|
	\| [Qwen3-1.7B-Coder-Distilled-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF) \| 194 \|

	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](https://huggingface.co/collections/reaperdoesntknow/distilqwen-69bf40ec669117e3f069ef1c) — 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](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) — 508 downloads

	Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org/10.57967/hf/8165)

	Convergent Intelligence LLC: Research Division

	<!-- CIX-CROSSLINK-END -->
	<!-- cix-keeper-ts:2026-05-21T13:16:02Z -->