Instructions to use principled-intelligence/Qwen3.5-2B-text-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use principled-intelligence/Qwen3.5-2B-text-only with Transformers:

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

pipe = pipeline("text-generation", model="principled-intelligence/Qwen3.5-2B-text-only")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("principled-intelligence/Qwen3.5-2B-text-only")
model = AutoModelForCausalLM.from_pretrained("principled-intelligence/Qwen3.5-2B-text-only")
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 principled-intelligence/Qwen3.5-2B-text-only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "principled-intelligence/Qwen3.5-2B-text-only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "principled-intelligence/Qwen3.5-2B-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/principled-intelligence/Qwen3.5-2B-text-only

SGLang

How to use principled-intelligence/Qwen3.5-2B-text-only 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 "principled-intelligence/Qwen3.5-2B-text-only" \
    --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": "principled-intelligence/Qwen3.5-2B-text-only",
		"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 "principled-intelligence/Qwen3.5-2B-text-only" \
        --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": "principled-intelligence/Qwen3.5-2B-text-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use principled-intelligence/Qwen3.5-2B-text-only with Docker Model Runner:
```
docker model run hf.co/principled-intelligence/Qwen3.5-2B-text-only
```

Something wrong with this one?

by KipTonic - opened Jun 16

Discussion

KipTonic

Jun 16

0.8B and 4B train successfully but this one doesn't, I get a weird recompile error in my python env. Using exact same script and dataset so the variable is this 2B model. There might be something wrong with your 2B text-only model.

edobobo

Principled Intelligence org about 1 month ago

•

edited about 1 month ago

Hey @KipTonic super strange, the upload is done in the exact same way for each model. I'll give it a look asap.

KipTonic

about 1 month ago

I'm getting a dynamo recompile error during training. Scratch what I said about 4B working, that one failed after 3 steps, the 2B failed immediately and I haven't tested the 0.8B for more than one step.
This doesn't happen for the original vision-capable Qwen models. Let me know if you need to see my script.

KipTonic

about 1 month ago

Never mind, it's happening with the base Qwen model now as well. I think it's an Unsloth bug.

edobobo

Principled Intelligence org 30 days ago

Ook!

edobobo changed discussion status to closed 30 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment