Instructions to use Michael-Kozu/Kuiper-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Michael-Kozu/Kuiper-R1 with Transformers:

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

pipe = pipeline("text-generation", model="Michael-Kozu/Kuiper-R1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Michael-Kozu/Kuiper-R1")
model = AutoModelForMultimodalLM.from_pretrained("Michael-Kozu/Kuiper-R1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Michael-Kozu/Kuiper-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Michael-Kozu/Kuiper-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Michael-Kozu/Kuiper-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Michael-Kozu/Kuiper-R1

SGLang

How to use Michael-Kozu/Kuiper-R1 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 "Michael-Kozu/Kuiper-R1" \
    --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": "Michael-Kozu/Kuiper-R1",
		"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 "Michael-Kozu/Kuiper-R1" \
        --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": "Michael-Kozu/Kuiper-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Michael-Kozu/Kuiper-R1 with Docker Model Runner:
```
docker model run hf.co/Michael-Kozu/Kuiper-R1
```

Kuiper-R1 / reports /EVAL_REPORT.md

Michael-Kozu

Upload reports/EVAL_REPORT.md with huggingface_hub

f8fb1ff verified 1 day ago

preview code

Raw

History Blame Contribute Delete

2.47 kB

Kuiper-R1 — Evaluation Report

Held-out benchmark: Jackrong/DeepSeek-V4-Distill-8000x (inverted). n=200 rows. Cross-lineage generalization: training teacher QwQ-32B (OpenThoughts3) vs benchmark teacher DeepSeek-V4-Flash (GLM-5.1 prompts) — disjoint lineages.

Decoding: temperature 0.4, thinking disabled (the reasoning-model base otherwise emits a <think> preamble that eats the token budget). Scorer is deterministic (stdlib).

Results: untouched base vs SFT vs ORPO (release)

Metric	Untouched base	Kuiper SFT	Kuiper ORPO (release)
final-answer preserved (exact)	0.155	0.805	0.820
final-answer preserved (soft)	0.735	0.805	0.825
format valid (3-tag contract)	0.980	0.850	0.880
no invented tool outputs	1.000	1.000	1.000
no contradiction	1.000	0.995	0.990
no repetition collapse	0.980	0.840	0.825
expansion quality (mean)	0.791	0.725	0.769
depth-to-concision (mean)	0.222	0.221	0.226
semantic consistency w/ bubbles (mean)	0.708	0.515	0.535
trace vs reference similarity (mean)	0.306	0.171	0.182
overall (mean)	0.329	0.492	0.504

Verdict

The fine-tune's decisive contribution is byte-exact final-answer preservation (0.155 → 0.820, a 5.3× gain), plus a higher overall score (0.504 vs 0.329). ORPO improves the SFT on format validity, expansion quality, semantic consistency, and answer preservation.

Honest caveat: the untouched base still scores higher on raw trace polish (format 0.980 vs 0.880; semantic consistency 0.708 vs 0.535). This is expected: Qwythos is a strong instruction-follower and the target format is spelled out in the system prompt, so it already produces well-formed, thoughtful traces — but it does not preserve the given final answer (0.155). Kuiper's value is teaching exact preservation while keeping trace quality close. Training on longer (un-truncated) traces and more data would close the remaining quality gap; both are single-GPU-time limited here (see model card).

Safety metrics are clean across the board: no invented tool outputs (1.000), no contradiction (~1.0), no repetition collapse (>0.82), and every output is an explicitly labeled <synthetic_trace> — no claim of being any proprietary model's real reasoning.

Release model: merged-fp16-orpo (best overall + best preservation).