Instructions to use precisionalgorithms/qwen3.5-9b_precision_agentic_trading with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use precisionalgorithms/qwen3.5-9b_precision_agentic_trading with Transformers:

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

pipe = pipeline("text-generation", model="precisionalgorithms/qwen3.5-9b_precision_agentic_trading")
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("precisionalgorithms/qwen3.5-9b_precision_agentic_trading")
model = AutoModelForMultimodalLM.from_pretrained("precisionalgorithms/qwen3.5-9b_precision_agentic_trading", 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 precisionalgorithms/qwen3.5-9b_precision_agentic_trading with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "precisionalgorithms/qwen3.5-9b_precision_agentic_trading"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "precisionalgorithms/qwen3.5-9b_precision_agentic_trading",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/precisionalgorithms/qwen3.5-9b_precision_agentic_trading

SGLang

How to use precisionalgorithms/qwen3.5-9b_precision_agentic_trading 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 "precisionalgorithms/qwen3.5-9b_precision_agentic_trading" \
    --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": "precisionalgorithms/qwen3.5-9b_precision_agentic_trading",
		"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 "precisionalgorithms/qwen3.5-9b_precision_agentic_trading" \
        --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": "precisionalgorithms/qwen3.5-9b_precision_agentic_trading",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use precisionalgorithms/qwen3.5-9b_precision_agentic_trading with Docker Model Runner:
```
docker model run hf.co/precisionalgorithms/qwen3.5-9b_precision_agentic_trading
```

precisionalgorithms commited on 12 days ago

Commit

3f64c14

verified ·

1 Parent(s): 2b94010

Raw eval output for both runs

Browse files

Files changed (5) hide show

eval/README.md +15 -0
eval/v3_base.json +0 -0
eval/v3_tuned.json +0 -0
eval/v4_base.json +0 -0
eval/v4_tuned.json +0 -0

eval/README.md ADDED Viewed

	@@ -0,0 +1,15 @@

+# Eval results
+Raw output from the harness so the numbers in the model card can be checked rather than
+taken on trust.
+- `v3_base.json` / `v3_tuned.json`: the released model against its base, 120 generated
+  cases, both bf16, identical serving settings. This is the pair the model card reports.
+- `v4_base.json` / `v4_tuned.json`: the later run that tried to fix the refusal rate by
+  rebalancing the training data and made it worse. Kept because the negative result is the
+  useful part.
+Reproduce with:
+    python -m pat.cli run --url <endpoint> --model <name> --generated 120 --gen-seed 1 --out out.json
+    python -m pat.cli compare v3_base.json v3_tuned.json

eval/v3_base.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval/v3_tuned.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval/v4_base.json ADDED Viewed

The diff for this file is too large to render. See raw diff

eval/v4_tuned.json ADDED Viewed

The diff for this file is too large to render. See raw diff