Instructions to use armand0e/Qwen3.5-9B-Agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use armand0e/Qwen3.5-9B-Agent with Transformers:

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

pipe = pipeline("image-text-to-text", model="armand0e/Qwen3.5-9B-Agent")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("armand0e/Qwen3.5-9B-Agent")
model = AutoModelForImageTextToText.from_pretrained("armand0e/Qwen3.5-9B-Agent")
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

vLLM

How to use armand0e/Qwen3.5-9B-Agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "armand0e/Qwen3.5-9B-Agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "armand0e/Qwen3.5-9B-Agent",
		"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/armand0e/Qwen3.5-9B-Agent

SGLang

How to use armand0e/Qwen3.5-9B-Agent 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 "armand0e/Qwen3.5-9B-Agent" \
    --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": "armand0e/Qwen3.5-9B-Agent",
		"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 "armand0e/Qwen3.5-9B-Agent" \
        --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": "armand0e/Qwen3.5-9B-Agent",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Studio new

How to use armand0e/Qwen3.5-9B-Agent with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for armand0e/Qwen3.5-9B-Agent to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for armand0e/Qwen3.5-9B-Agent to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for armand0e/Qwen3.5-9B-Agent to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="armand0e/Qwen3.5-9B-Agent",
    max_seq_length=2048,
)

Docker Model Runner
How to use armand0e/Qwen3.5-9B-Agent with Docker Model Runner:
```
docker model run hf.co/armand0e/Qwen3.5-9B-Agent
```

Qwen3.5-9B-Agent / README.md

armand0e

Update README.md

6c2396c verified 8 days ago

preview code

raw

history blame contribute delete

4.41 kB

	---
	base_model: unsloth/Qwen3.5-9B
	tags:
	- text-generation-inference
	- transformers
	- unsloth
	- qwen3_5
	- agent
	license: apache-2.0
	language:
	- en
	datasets:
	- armand0e/badlogicgames-pi-mono-opus-filtered
	- armand0e/kimi-k2.6-claude-code-traces
	- armand0e/kimi-k2.6-agent
	- armand0e/minimax-m2.7-agent
	- TeichAI/Claude-Opus-4.6-Reasoning-887x
	---

	This model was trained on the following datasets using the qwen3.6 chat template (training was done with enable_thinking and preserve_thinking set to `True`):

	- `armand0e/badlogicgames-pi-mono-opus-filtered` - Pi traces from Claude Opus (mainly 4.5)
	- `armand0e/kimi-k2.6-claude-code-traces` - Claude Code traces from kimi k2.6
	- `armand0e/kimi-k2.6-agent` - Codex traces from kimi k2.6
	- `armand0e/minimax-m2.7-agent` - Pi traces from minimax m2.7
	- `TeichAI/Claude-Opus-4.6-Reasoning-887x` (Downsampled to 200 examples, only present to stabilize chat behavior)

	For now this model is just a test to make sure the `teich` package was working correctly. less than 400 examples were given to the model in this training run so expect an overall performance degradation. A much more comprehensive DeepSeek Coder will be released in the coming days once training is complete

	I recommend using the following sampling parameters:

	- temp: 1.0
	- top_k: 20 (though higher values like 40 still seem to work and be stable with tool calling and agentic tasks)
	- top_p: 0.95
	- min_p: 0.00
	- repeat_penalty: 1.0
	- presence_penalty: 1.5

	Training code:

	```py
	MAX_SEQ_LEN = 49152

	from unsloth import FastModel
	import torch

	model = FastModel.get_peft_model(
	model,
	finetune_vision_layers = False, # Turn off for just text!
	finetune_language_layers = True, # Should leave on!
	finetune_attention_modules = True, # Attention good for GRPO
	finetune_mlp_modules = True, # Should leave on always!

	r = 64, # Larger = higher accuracy, but might overfit
	lora_alpha = 64, # Recommended alpha == r at least
	lora_dropout = 0,
	bias = "none",
	random_state = 3407,
	)

	from teich import prepare_data

	train_dataset = prepare_data(
	{
	"opus-agent": {
	"source": "armand0e/badlogicgames-pi-mono-opus-filtered",
	},
	"kimi-claude": {
	"source": "armand0e/kimi-k2.6-claude-code-traces",
	},
	"kimi-codex": {
	"source": "armand0e/kimi-k2.6-agent",
	},
	"minimax-m2.7": {
	"source": "armand0e/minimax-m2.7-agent",
	},
	"chat": {
	"source": "TeichAI/Claude-Opus-4.6-Reasoning-887x",
	"max_examples": 200,
	}
	},
	tokenizer,
	split="train",
	hf_token=HF_TOKEN,
	chat_template_kwargs={"enable_thinking": True, "preserve_thinking": True},
	max_length=MAX_SEQ_LEN,
	drop_oversized_examples=True,
	trim_oversized_followups=True,
	tokenize=True,
	strict=True,
	)

	from trl import SFTConfig, SFTTrainer

	trainer = SFTTrainer(
	model=model,
	tokenizer=tokenizer,
	train_dataset=train_dataset,
	eval_dataset=None,
	args=SFTConfig(
	dataset_text_field="text",
	dataset_num_proc=1,
	max_length=MAX_SEQ_LEN,
	packing=False,
	per_device_train_batch_size=1,
	gradient_accumulation_steps=8,
	warmup_steps= 5,
	num_train_epochs=2,
	learning_rate=2e-4,
	logging_steps=1,
	save_steps=100,
	save_total_limit=3,
	optim="adamw_8bit",
	weight_decay=0.01,
	lr_scheduler_type="linear",
	output_dir=OUTPUT_DIR,
	seed=3407,
	report_to="none",
	),
	)

	from teich import mask_data

	trainer = mask_data(
	trainer,
	tokenizer=tokenizer,
	train_on_reasoning=True,
	train_on_final_answers=True,
	train_on_tools=True,
	)
	```

	This tune was very data limited, but still impresses me. I encourage everyone to generate their own high quality data for their own use cases, they can all be aggregated together.

	---
	# Uploaded finetuned model

	- Developed by: armand0e
	- License: apache-2.0
	- Finetuned from model : unsloth/Qwen3.5-9B

	This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)