Instructions to use AItonomy/PhAI-IDE-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AItonomy/PhAI-IDE-72B with Transformers:

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

pipe = pipeline("text-generation", model="AItonomy/PhAI-IDE-72B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AItonomy/PhAI-IDE-72B")
model = AutoModelForCausalLM.from_pretrained("AItonomy/PhAI-IDE-72B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AItonomy/PhAI-IDE-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AItonomy/PhAI-IDE-72B"
# 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-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AItonomy/PhAI-IDE-72B

SGLang

How to use AItonomy/PhAI-IDE-72B 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-72B" \
    --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-72B",
		"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 "AItonomy/PhAI-IDE-72B" \
        --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-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AItonomy/PhAI-IDE-72B with Docker Model Runner:
```
docker model run hf.co/AItonomy/PhAI-IDE-72B
```

Update PhAI-IDE-72B model card

by leyili6666 - opened 22 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ tags:
 **PhAI-IDE-72B** is a supervised fine-tune of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) for scientific coding and interaction with tools, trained using [ms-swift](https://github.com/modelscope/ms-swift). The release contains full BF16 weights with the final LoRA adapter merged.
-The training data is sourced from [AItonomy/ScienceIDE](https://huggingface.co/datasets/AItonomy/ScienceIDE). This model uses **Codex-only repaired trajectories v3 for 3 epochs**.
 ## Quick start
@@ -32,7 +32,7 @@ Use Transformers 5.16.1, PyTorch and Accelerate. The example loads the model, co
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-model_id = "leyili6666/PhAI-IDE-72B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id, dtype="bfloat16", device_map="auto",
@@ -84,7 +84,7 @@ Training uses **ms-swift** supervised fine-tuning with **LoRA across trainable l
 | Setting | Value |
 | --- | --- |
-| Training subset | Codex-only repaired trajectories v3 |
 | Training examples / tasks | 4,567 segments / 564 tasks |
 | Validation examples / tasks | 544 segments / 81 tasks |
 | Train/validation task overlap | 0 |

 **PhAI-IDE-72B** is a supervised fine-tune of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) for scientific coding and interaction with tools, trained using [ms-swift](https://github.com/modelscope/ms-swift). The release contains full BF16 weights with the final LoRA adapter merged.
+The training data is sourced from [AItonomy/ScienceIDE](https://huggingface.co/datasets/AItonomy/ScienceIDE).
 ## Quick start
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+model_id = "AItonomy/PhAI-IDE-72B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id, dtype="bfloat16", device_map="auto",
 | Setting | Value |
 | --- | --- |
+| Training dataset | Codex trajectories |
 | Training examples / tasks | 4,567 segments / 564 tasks |
 | Validation examples / tasks | 544 segments / 81 tasks |
 | Train/validation task overlap | 0 |