Instructions to use ayjays132/Phillnet-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayjays132/Phillnet-2 with Transformers:

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

pipe = pipeline("text-generation", model="ayjays132/Phillnet-2", trust_remote_code=True)
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("ayjays132/Phillnet-2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ayjays132/Phillnet-2", trust_remote_code=True, 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 ayjays132/Phillnet-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayjays132/Phillnet-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayjays132/Phillnet-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ayjays132/Phillnet-2

SGLang

How to use ayjays132/Phillnet-2 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 "ayjays132/Phillnet-2" \
    --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": "ayjays132/Phillnet-2",
		"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 "ayjays132/Phillnet-2" \
        --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": "ayjays132/Phillnet-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ayjays132/Phillnet-2 with Docker Model Runner:
```
docker model run hf.co/ayjays132/Phillnet-2
```

Phillnet-2 / memory_optimization /test.py

ayjays132

Upload 478 files

101858b verified 6 months ago

Raw History Blame Contribute Delete

2.34 kB

"""
Memory Optimization Module Test
Quick test to verify all components work correctly.
"""
import torch
import sys
import os

# Add parent directory to path
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from memory_optimization import (
    UnifiedMemoryManager,
    MemoryOptimizationConfig,
    get_shared_model,
    get_tensor,
    return_tensor,
    get_memory_stats,
    clear_memory
)

def test_memory_optimization():
    """Test memory optimization module"""
    print("=" * 70)
    print("Testing Memory Optimization Module")
    print("=" * 70)
    
    # Initialize config
    config = MemoryOptimizationConfig(
        use_shared_model=True,
        device="cuda" if torch.cuda.is_available() else "cpu"
    )
    
    print(f"\n[CONFIG] Device: {config.device}")
    print(f"[CONFIG] Shared Model: {config.use_shared_model}")
    
    # Initialize manager
    manager = UnifiedMemoryManager(config)
    print("\n[OK] UnifiedMemoryManager initialized")
    
    # Test tensor pooling
    print("\n[TEST] Tensor Pooling...")
    tensor1 = manager.get_tensor((10, 1024), dtype=torch.float32)
    print(f"  [OK] Created tensor: {tensor1.shape}, device: {tensor1.device}")
    
    manager.return_tensor(tensor1)
    print("  [OK] Returned tensor to pool")
    
    tensor2 = manager.get_tensor((10, 1024), dtype=torch.float32)
    print(f"  [OK] Retrieved tensor from pool: {tensor2.shape}")
    
    # Test shared model (if available)
    print("\n[TEST] Shared Model...")
    try:
        # This will use shared Qwen model if available
        model = manager.get_shared_model("Qwen/Qwen3-0.6B", "transformer")
        print(f"  [OK] Got shared model: {type(model).__name__}")
    except Exception as e:
        print(f"  [WARN] Could not get shared model: {e}")
    
    # Test memory stats
    print("\n[TEST] Memory Stats...")
    stats = manager.get_memory_stats()
    print(f"  [OK] Got memory stats: {len(stats)} categories")
    
    # Test cleanup
    print("\n[TEST] Memory Cleanup...")
    manager.clear_all_memory()
    print("  [OK] Memory cleared")
    
    print("\n" + "=" * 70)
    print("[SUCCESS] All tests passed!")
    print("=" * 70)

if __name__ == "__main__":
    test_memory_optimization()

	"""
	Memory Optimization Module Test
	Quick test to verify all components work correctly.
	"""
	import torch
	import sys
	import os

	# Add parent directory to path
	sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

	from memory_optimization import (
	UnifiedMemoryManager,
	MemoryOptimizationConfig,
	get_shared_model,
	get_tensor,
	return_tensor,
	get_memory_stats,
	clear_memory
	)

	def test_memory_optimization():
	"""Test memory optimization module"""
	print("=" * 70)
	print("Testing Memory Optimization Module")
	print("=" * 70)

	# Initialize config
	config = MemoryOptimizationConfig(
	use_shared_model=True,
	device="cuda" if torch.cuda.is_available() else "cpu"
	)

	print(f"\n[CONFIG] Device: {config.device}")
	print(f"[CONFIG] Shared Model: {config.use_shared_model}")

	# Initialize manager
	manager = UnifiedMemoryManager(config)
	print("\n[OK] UnifiedMemoryManager initialized")

	# Test tensor pooling
	print("\n[TEST] Tensor Pooling...")
	tensor1 = manager.get_tensor((10, 1024), dtype=torch.float32)
	print(f" [OK] Created tensor: {tensor1.shape}, device: {tensor1.device}")

	manager.return_tensor(tensor1)
	print(" [OK] Returned tensor to pool")

	tensor2 = manager.get_tensor((10, 1024), dtype=torch.float32)
	print(f" [OK] Retrieved tensor from pool: {tensor2.shape}")

	# Test shared model (if available)
	print("\n[TEST] Shared Model...")
	try:
	# This will use shared Qwen model if available
	model = manager.get_shared_model("Qwen/Qwen3-0.6B", "transformer")
	print(f" [OK] Got shared model: {type(model).__name__}")
	except Exception as e:
	print(f" [WARN] Could not get shared model: {e}")

	# Test memory stats
	print("\n[TEST] Memory Stats...")
	stats = manager.get_memory_stats()
	print(f" [OK] Got memory stats: {len(stats)} categories")

	# Test cleanup
	print("\n[TEST] Memory Cleanup...")
	manager.clear_all_memory()
	print(" [OK] Memory cleared")

	print("\n" + "=" * 70)
	print("[SUCCESS] All tests passed!")
	print("=" * 70)

	if __name__ == "__main__":
	test_memory_optimization()