Instructions to use LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32 with Transformers:

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

pipe = pipeline("text-generation", model="LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32")
model = AutoModelForMultimodalLM.from_pretrained("LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32

SGLang

How to use LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32 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 "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32" \
    --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": "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32",
		"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 "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32" \
        --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": "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32 with Docker Model Runner:
```
docker model run hf.co/LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32
```

OPSD-PI Qwen3.5-9B Strong Trailing — update 32

This public repository is the directly loadable, fully merged Hugging Face model after 32 completed optimizer updates (zero-indexed training iteration 31). It comes from the 1024-row Strong PI trailing_user OPSD run on 8×RTX A6000.

The four model shards contain the merged expert-SFT initialization, the OPSD main-model LoRA update, the MTP LoRA update, and every directly trained full-MTP tensor. No adapter or additional merge step is required.

Load

from transformers import AutoModelForCausalLM, AutoProcessor

repo = "LSW142857/OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update32"
processor = AutoProcessor.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

Integrity and provenance

Run sha256sum -c SHA256SUMS after downloading the repository. All 775 output tensors were checked exactly before upload. The merge restores full trained MTP tensors first and then applies main-model and MTP LoRA deltas with scaling 2.0. See merge_manifest.json and training_config.json for hashes, source identity, configuration, and the finite metrics from this update.

The PI was teacher-only during training. Evaluate the student without adding PI, and use held-out tasks rather than the 1024 training rows.

Downloads last month: -

Safetensors

Model size

10B params

Tensor type

BF16