Instructions to use Jackrong/Qwopus3.5-9B-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jackrong/Qwopus3.5-9B-Coder with Transformers:

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

pipe = pipeline("image-text-to-text", model="Jackrong/Qwopus3.5-9B-Coder")
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("Jackrong/Qwopus3.5-9B-Coder")
model = AutoModelForImageTextToText.from_pretrained("Jackrong/Qwopus3.5-9B-Coder")
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 Jackrong/Qwopus3.5-9B-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jackrong/Qwopus3.5-9B-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jackrong/Qwopus3.5-9B-Coder",
		"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/Jackrong/Qwopus3.5-9B-Coder

SGLang

How to use Jackrong/Qwopus3.5-9B-Coder 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 "Jackrong/Qwopus3.5-9B-Coder" \
    --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": "Jackrong/Qwopus3.5-9B-Coder",
		"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 "Jackrong/Qwopus3.5-9B-Coder" \
        --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": "Jackrong/Qwopus3.5-9B-Coder",
		"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 Jackrong/Qwopus3.5-9B-Coder 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 Jackrong/Qwopus3.5-9B-Coder 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 Jackrong/Qwopus3.5-9B-Coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jackrong/Qwopus3.5-9B-Coder to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Jackrong/Qwopus3.5-9B-Coder",
    max_seq_length=2048,
)

Docker Model Runner
How to use Jackrong/Qwopus3.5-9B-Coder with Docker Model Runner:
```
docker model run hf.co/Jackrong/Qwopus3.5-9B-Coder
```

Jackrong commited on 8 days ago

Commit

2f5d9a2

verified ·

1 Parent(s): e744108

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -2

README.md CHANGED Viewed

@@ -185,7 +185,6 @@ BugFind-15 is a test set containing 15 scenarios from shallow to deep, aiming to
 > [!IMPORTANT]
 > All tests were conducted with a temperature of 1 as officially recommended by qwen3.5. All errors and model issues were attempted to be regenerated twice after a test failure. If both attempts fail, it is considered a failure.
 > Screenshots of all test interfaces are uploaded to the image folder of the repository.
@@ -211,8 +210,8 @@ To break through this limitation, we adopted the **Trace Inversion** technology.
 #### 2. GLM-5.1 Agent Real Trace Data: lambda/hermes-agent-reasoning-traces
 To significantly enhance the model's execution and coding capabilities in real environments, this model additionally introduced the **`lambda/hermes-agent-reasoning-traces`** dataset.
-![Screenshot 2026-05-16 at 5.06.53 PM](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/_U04B3HyUY403mQpW9Mz2.png)
 - **Data Source and Scale**: This data subset contains approximately 10,000 high-quality multi-turn Tool Calling Trajectories generated based on the ZhipuAI GLM-5.1 and kimi-4.6 models.
 - **Real Agent Behavior**: Unlike traditional synthetic data, these samples represent real Agent conversations. Each sample not only contains the step-by-step reasoning process in the `<think>` tags, but also includes actual tool execution results (rather than fabricated outputs out of thin air).
@@ -291,6 +290,17 @@ The training of this model integrates a phased learning pipeline of **Trace Inve
 > [!NOTE]
 > Because agent trajectory datasets are complex and diverse. The datasets have undergone rigorous cleaning and formatting.
 ---
 ## 🤝 Collaboration & Training Details

 > [!IMPORTANT]
 > All tests were conducted with a temperature of 1 as officially recommended by qwen3.5. All errors and model issues were attempted to be regenerated twice after a test failure. If both attempts fail, it is considered a failure.
 > Screenshots of all test interfaces are uploaded to the image folder of the repository.
 #### 2. GLM-5.1 Agent Real Trace Data: lambda/hermes-agent-reasoning-traces
 To significantly enhance the model's execution and coding capabilities in real environments, this model additionally introduced the **`lambda/hermes-agent-reasoning-traces`** dataset.
+![Screenshot 2026-05-16 at 5.34.59 PM](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/BTusWFqYaOS5GmRYvBuPq.png)
 - **Data Source and Scale**: This data subset contains approximately 10,000 high-quality multi-turn Tool Calling Trajectories generated based on the ZhipuAI GLM-5.1 and kimi-4.6 models.
 - **Real Agent Behavior**: Unlike traditional synthetic data, these samples represent real Agent conversations. Each sample not only contains the step-by-step reasoning process in the `<think>` tags, but also includes actual tool execution results (rather than fabricated outputs out of thin air).
 > [!NOTE]
 > Because agent trajectory datasets are complex and diverse. The datasets have undergone rigorous cleaning and formatting.
+## 🎯 Three-Stage Curriculum Learning
+**Qwopus3.5-9B-coder** adopts a phased reasoning data mixture strategy similar to Curriculum Learning, gradually increasing the difficulty and complexity of training signals:
+1. **Early Stage (Format Establishment):** Focuses on short-to-medium length reasoning samples with stable formats. The primary goal of this stage is to establish a reliable, structured new reasoning format while avoiding overwhelming the model with extreme complexity.
+2. **Middle Stage (Complexity Scaling & Multi-Teacher Distillation):** Gradually increases the proportion of complex reasoning samples from multiple teacher models.
+   - The distillation data is sourced from more powerful models whose style distribution closely matches the base model, ensuring that the capability gap is not too wide, thereby achieving efficient learning.
+3. **Late Stage (Long-Context Reinforcement & Drift Prevention):** Reinforces reasoning capabilities in long contexts. Crucially, this stage retains **short-sample replay** to ensure the model maintains its short-context instruction-following capability and minimizes capability drift.
 ---
 ## 🤝 Collaboration & Training Details