Instructions to use 4fhct4sd/qwen3.5-4b-posture with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 4fhct4sd/qwen3.5-4b-posture with Transformers:

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

pipe = pipeline("text-generation", model="4fhct4sd/qwen3.5-4b-posture")
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("4fhct4sd/qwen3.5-4b-posture")
model = AutoModelForMultimodalLM.from_pretrained("4fhct4sd/qwen3.5-4b-posture", 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

vLLM

How to use 4fhct4sd/qwen3.5-4b-posture with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "4fhct4sd/qwen3.5-4b-posture"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "4fhct4sd/qwen3.5-4b-posture",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/4fhct4sd/qwen3.5-4b-posture

SGLang

How to use 4fhct4sd/qwen3.5-4b-posture 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 "4fhct4sd/qwen3.5-4b-posture" \
    --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": "4fhct4sd/qwen3.5-4b-posture",
		"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 "4fhct4sd/qwen3.5-4b-posture" \
        --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": "4fhct4sd/qwen3.5-4b-posture",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use 4fhct4sd/qwen3.5-4b-posture with Docker Model Runner:
```
docker model run hf.co/4fhct4sd/qwen3.5-4b-posture
```

Qwen3.5-4B Posture — merged model

Final phase 2 LoRA adapter merged into Qwen/Qwen3.5-4B, exported as 16-bit safetensors. The adapter continues phase 1 (scatter) with phase 2 (crystal) training.

Adapters and resumable checkpoints: https://huggingface.co/4fhct4sd/qwen3.5-4b-posture-checkpoints

Use Transformers 5.5.0 for the tested inference runtime. The local Studio 5.3.0 sidecar produced invalid-probability CUDA assertions during multi-turn chat; 5.5.0 passed a five-turn test. This is limited validation, not a general quality or stability guarantee. The model may invent conversational turns; generated claims about itself are not verified facts.

No evaluation benchmark has been run. Training data is not included in this repository.

Downloads last month: 206

Safetensors

Model size

5B params

Tensor type

BF16

F32

Model tree for 4fhct4sd/qwen3.5-4b-posture

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(941)

this model