Instructions to use AItonomy/PhAI-IDE-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AItonomy/PhAI-IDE-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="AItonomy/PhAI-IDE-9B")
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("AItonomy/PhAI-IDE-9B")
model = AutoModelForMultimodalLM.from_pretrained("AItonomy/PhAI-IDE-9B", 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 AItonomy/PhAI-IDE-9B with vLLM:

Install from pip and serve model

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

SGLang

How to use AItonomy/PhAI-IDE-9B 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 "AItonomy/PhAI-IDE-9B" \
    --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": "AItonomy/PhAI-IDE-9B",
		"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 "AItonomy/PhAI-IDE-9B" \
        --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": "AItonomy/PhAI-IDE-9B",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use AItonomy/PhAI-IDE-9B with Docker Model Runner:
```
docker model run hf.co/AItonomy/PhAI-IDE-9B
```

Update README with verified ScienceAccelBench results

by leyili6666 - opened 2 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+11

-26

Files changed (1) hide show

README.md +11 -26

README.md CHANGED Viewed

@@ -25,15 +25,15 @@ The training data is sourced from [AItonomy/ScienceIDE](https://huggingface.co/d
 ## Quick start
-Use Transformers 5.16.1, PyTorch and Accelerate. The example loads the model, configuration and tokenizer directly from this repository. Sign in with `hf auth login` to access this private repository.
 ```python
 from transformers import AutoTokenizer, AutoModelForImageTextToText
 model_id = "AItonomy/PhAI-IDE-9B"
-tokenizer = AutoTokenizer.from_pretrained(model_id, token=True)
 model = AutoModelForImageTextToText.from_pretrained(
-    model_id, dtype="bfloat16", device_map="auto", token=True,
 )
 inputs = tokenizer.apply_chat_template(
     [{"role": "user", "content": "Explain how to verify a numerical simulation."}],
@@ -45,32 +45,17 @@ print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_to
 BF16 weights occupy approximately 18.82 GB, plus runtime memory and KV cache.
-## Benchmark performance
-### Score improvements
-Scores (%); gains in percentage points.
-| Benchmark | Qwen/Qwen3.5-9B | PhAI-IDE-9B | Gain (pp) |
-| --- | ---: | ---: | ---: |
-| BBH word-sorting | 25.60 | **60.40** | **+34.80** |
-| AQuA-RAT | 86.61 | **88.98** | **+2.36** |
-| MATH-500 | 91.40 | **92.20** | **+0.80** |
-| OpenBookQA (128-sample subset) | 33.59 | **35.16** | **+1.56** |
-| GSM8K (128-sample subset) | 89.84 | **92.97** | **+3.12** |
-### Comparison with published models
-Scores (%); evaluation settings vary by source.
-| Benchmark | Reference model | Parameters | Published score | PhAI-IDE-9B result | Source |
-| --- | --- | ---: | ---: | ---: | --- |
-| GSM8K | Llama-3.1-8B-Instruct | 8B | 84.5 | **92.97** | [Meta model card](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct#instruction-tuned-models) |
-| GSM8K | Qwen2.5-7B-Instruct | 7B | 91.6 | **92.97** | [Qwen2.5 report, Table 8](https://arxiv.org/html/2412.15115v2#S5.SS2.SSS1) |
-| GSM8K | Gemma-2-9B-IT | 9B | 76.7 | **92.97** | [Qwen2.5 report, Table 8](https://arxiv.org/html/2412.15115v2#S5.SS2.SSS1) |
-| GSM8K | SciTulu-7B | 7B | 29.5 | **92.97** | [SciRIFF report, Table 7](https://arxiv.org/html/2406.07835v2#A3) |
-| BBH word-sorting | Llama-3.1-8B-Instruct | 8.03B | 51.2 | **60.40** | [BenchLM independent results](https://huggingface.co/spaces/steampunque/benchlm/blob/d45e8600172857935610426f797a4429f2f136d6/README.md) |
-| BBH word-sorting | Qwen2.5-7B-Instruct | 7.62B | 15.6 | **60.40** | [BenchLM independent results](https://huggingface.co/spaces/steampunque/benchlm/blob/d45e8600172857935610426f797a4429f2f136d6/README.md) |
 ## Training procedure

 ## Quick start
+Use Transformers 5.16.1, PyTorch and Accelerate. The example loads the model, configuration and tokenizer directly from this repository.
 ```python
 from transformers import AutoTokenizer, AutoModelForImageTextToText
 model_id = "AItonomy/PhAI-IDE-9B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
+    model_id, dtype="bfloat16", device_map="auto",
 )
 inputs = tokenizer.apply_chat_template(
     [{"role": "user", "content": "Explain how to verify a numerical simulation."}],
 BF16 weights occupy approximately 18.82 GB, plus runtime memory and KV cache.
+## ScienceAccelBench performance
+Across all 27 ScienceAccelBench environments, the task-pooled pass rate increases from **17.09% to 20.89% (+3.80 percentage points)** on **158 valid paired tasks**.
+Task-held-out, localized scientific-code repair on familiar codebases, with original numerical verification. Pass rates (%); gains in percentage points.
+| Environment | Tasks | Qwen3.5-9B | PhAI-IDE-9B | Gain (pp) |
+| --- | ---: | ---: | ---: | ---: |
+| laps | 16 | 31.25 | **50.00** | **+18.75** |
+| mitgcm-biogeo | 8 | 0.00 | **12.50** | **+12.50** |
+| pluto-rmhd-resrmhd | 7 | 0.00 | **28.57** | **+28.57** |
 ## Training procedure