Instructions to use RocketData/Qwen3.5-4B-rocketdata with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RocketData/Qwen3.5-4B-rocketdata with Transformers:

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

pipe = pipeline("image-text-to-text", model="RocketData/Qwen3.5-4B-rocketdata")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RocketData/Qwen3.5-4B-rocketdata")
model = AutoModelForMultimodalLM.from_pretrained("RocketData/Qwen3.5-4B-rocketdata", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RocketData/Qwen3.5-4B-rocketdata with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RocketData/Qwen3.5-4B-rocketdata:BF16
# Run inference directly in the terminal:
llama cli -hf RocketData/Qwen3.5-4B-rocketdata:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RocketData/Qwen3.5-4B-rocketdata:BF16
# Run inference directly in the terminal:
llama cli -hf RocketData/Qwen3.5-4B-rocketdata:BF16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf RocketData/Qwen3.5-4B-rocketdata:BF16
# Run inference directly in the terminal:
./build/bin/llama cli -hf RocketData/Qwen3.5-4B-rocketdata:BF16

Use Docker

docker model run hf.co/RocketData/Qwen3.5-4B-rocketdata:BF16

Llama new
LM Studio
Jan

vLLM

How to use RocketData/Qwen3.5-4B-rocketdata with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RocketData/Qwen3.5-4B-rocketdata"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RocketData/Qwen3.5-4B-rocketdata",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RocketData/Qwen3.5-4B-rocketdata:BF16

SGLang

How to use RocketData/Qwen3.5-4B-rocketdata 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 "RocketData/Qwen3.5-4B-rocketdata" \
    --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": "RocketData/Qwen3.5-4B-rocketdata",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "RocketData/Qwen3.5-4B-rocketdata" \
        --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": "RocketData/Qwen3.5-4B-rocketdata",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use RocketData/Qwen3.5-4B-rocketdata with Ollama:
```
ollama run hf.co/RocketData/Qwen3.5-4B-rocketdata:BF16
```
Unsloth Desktop

How to use RocketData/Qwen3.5-4B-rocketdata with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RocketData/Qwen3.5-4B-rocketdata:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RocketData/Qwen3.5-4B-rocketdata:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RocketData/Qwen3.5-4B-rocketdata with Docker Model Runner:
```
docker model run hf.co/RocketData/Qwen3.5-4B-rocketdata:BF16
```

Lemonade

How to use RocketData/Qwen3.5-4B-rocketdata with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RocketData/Qwen3.5-4B-rocketdata:BF16

Run and chat with the model

lemonade run user.Qwen3.5-4B-rocketdata-BF16

List all available models

lemonade list

Hermes Agent

How to use RocketData/Qwen3.5-4B-rocketdata with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RocketData/Qwen3.5-4B-rocketdata:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RocketData/Qwen3.5-4B-rocketdata:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RocketData/Qwen3.5-4B-rocketdata with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RocketData/Qwen3.5-4B-rocketdata:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RocketData/Qwen3.5-4B-rocketdata:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.5-4B-rocketdata

Qwen/Qwen3.5-4B fine-tuned with Unsloth (16-bit LoRA) to design model rockets from flight requirements. Given a request such as "a rocket that reaches about 450 m on an F50T", it writes its reasoning in <thought>…</thought> and then a design as JSON in <design>…</design>.

Trained on new_results/sft_v2.jsonl from Phorceon/rocketdata, minus the 12 designs with 60 or more parts (151 rows, 73 rockets). Code, every run tried and full results: sft/README.md in that repo (PR #10).

Files

Path	What it is
(top level)	Merged 16-bit weights in Hugging Face format; load with `from_pretrained("RocketData/Qwen3.5-4B-rocketdata")`
`gguf/Qwen3.5-4B-rocketdata.Q8_0.gguf`	The model for llama.cpp, LM Studio or Unsloth Studio (4.3 GB)
`gguf/Qwen3.5-4B-rocketdata.BF16-mmproj.gguf`	Image encoder; Studio and LM Studio want it next to the model (645 MB)
`lora/`	The LoRA adapter alone (needs `Qwen/Qwen3.5-4B` as the base); start here for more training or RL
`design.gbnf`	llama.cpp grammar that keeps every answer in the `<thought>…</thought><design>{json}</design>` format with valid JSON
`eval/`	Every scored answer behind the results below (`results_*.json`)
`train_log.json`	Loss history and the exact training settings

Use the 8-bit GGUF: the 4-bit (Q4_K_M) version broke the JSON brackets on most answers in testing.

How to use it

Thinking off. The model was trained with its reasoning in the answer, not in Qwen's thinking slot.
Temperature 0.7, top-p 0.95, top-k 20. At 0.3 it gets stuck in loops.
No presence or repetition penalty; JSON repeats keys constantly and any penalty breaks it.
The grammar design.gbnf wherever the app supports one (llama.cpp --grammar-file, the grammar field of a llama-server request, vLLM guided decoding).
System prompt (the one from the training data):

You are an autonomous aerospace design engineer. When given flight requirements, you must first calculate the required propulsion, stability, and descent parameters, then output the final verified hardware blueprint in JSON format inside tags.

Unsloth Studio: put the two .gguf files in one folder under %USERPROFILE%\.unsloth\studio\exports\ and turn thinking off. Studio's chat has no grammar option, so expect more broken JSON there than in the results below.

Results

On the 105 RL prompts in data/splits/rl_heldout.jsonl (the earlier Agents-A1-4B fine-tune in brackets):

Check	This model	Agents-A1-4B
Valid design JSON	103	103
Uses the project's schema	101	90
Uses the motor the prompt asked for	28 of 29	28 of 29
Stuck in a loop	2	0
Most common motor	A8 in 17% of designs, 42 motors in all	GragasMAY24 in about 74%

On the 38 test prompts in new_results/sft_test_v2.jsonl, over 3 runs: valid JSON 36–38, schema 36–37, asked-for motor 10–11 of 11. Without the grammar, the same file writes 93 valid designs of 105 instead of 103.

Known gaps

It makes up motor names in about a third of its designs; the training answers use only 66 motors.
A few answers still loop, always on a part list that never ends, and how many depends on the training run (another seed of the same recipe looped on 14 of 105).
No design has been simulated. The "Simulated apogee" in its reasoning is its own claim, and this design format records no part positions, so it can't be built in OpenRocket faithfully.

Training

16-bit LoRA, rank 16, alpha 16, learning rate 2e-4, batch 1 × gradient accumulation 8, 3 epochs (57 steps, 3.8 minutes on an RTX 5080), seed 42, last epoch kept. Test loss by epoch: 0.499, 0.452, 0.450. Unsloth 2026.10.7, transformers 5.5.0, TRL 0.23.1.

Downloads last month: 76

Safetensors

Model size

5B params

Tensor type

BF16

F32

Model tree for RocketData/Qwen3.5-4B-rocketdata

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(1,029)

this model