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
```

armand0e commited on 11 days ago

Commit

aad730d

verified ·

1 Parent(s): 852e726

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -6

README.md CHANGED Viewed

@@ -9,15 +9,21 @@ tags:
 license: apache-2.0
 language:
 - en
 ---
 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)
 Training specs:
 ```
@@ -112,6 +118,8 @@ trainer = mask_data(
 )
 ```
 ---
 # Uploaded finetuned  model
@@ -121,4 +129,4 @@ trainer = mask_data(
 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)

 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)
 Training specs:
 ```
 )
 ```
+  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
 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)