Text Generation
Transformers
Diffusers
Safetensors
English
gpt_oss
phillnet-2
gpt-oss
multimodal
image-generation
video-generation
speech
audio
custom-code
conversational
custom_code
Instructions to use ayjays132/Phillnet-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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)# 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) 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- 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
| import argparse | |
| import json | |
| from pathlib import Path | |
| from guidance_sidecar import GuidanceEngine, GuidanceSettings | |
| def main() -> None: | |
| parser = argparse.ArgumentParser(description="Local Hugging Face coding guidance sidecar") | |
| subparsers = parser.add_subparsers(dest="command", required=True) | |
| guide_parser = subparsers.add_parser("guide", help="Ask the local guidance model for structured coding help") | |
| guide_parser.add_argument("--task", required=True) | |
| guide_parser.add_argument("--context", default="") | |
| guide_parser.add_argument("--project", action="store_true") | |
| guide_parser.add_argument("--root", default=".") | |
| guide_parser.add_argument("--model", default=None) | |
| guide_parser.add_argument("--adapter", default=None) | |
| guide_parser.add_argument("--bundle", default=None, help="Path to an HF bundle containing base_model/") | |
| guide_parser.add_argument("--keep-loaded-seconds", type=int, default=None) | |
| guide_parser.add_argument("--no-cache", action="store_true") | |
| smoke_parser = subparsers.add_parser("smoke", help="Run one guidance request and save JSON result") | |
| smoke_parser.add_argument("--task", default="Add input validation and tests for a Python function without changing public API.") | |
| smoke_parser.add_argument("--output", default="./runtime/guidance_smoke_result.json") | |
| args = parser.parse_args() | |
| if args.command == "guide": | |
| if args.bundle: | |
| engine = GuidanceEngine.from_bundle(args.bundle) | |
| else: | |
| engine = GuidanceEngine( | |
| model_name=args.model, | |
| adapter_dir=args.adapter, | |
| keep_loaded_seconds=args.keep_loaded_seconds, | |
| ) | |
| result = ( | |
| engine.advise_project(args.task, root=args.root, use_cache=not args.no_cache) | |
| if args.project | |
| else engine.advise(args.task, args.context, use_cache=not args.no_cache) | |
| ) | |
| print(json.dumps(result, indent=2)) | |
| elif args.command == "smoke": | |
| engine = GuidanceEngine(GuidanceSettings(max_new_tokens=384)) | |
| result = engine.advise_project(args.task) | |
| output = Path(args.output) | |
| output.parent.mkdir(parents=True, exist_ok=True) | |
| output.write_text(json.dumps(result, indent=2), encoding="utf-8") | |
| print(json.dumps(result, indent=2)) | |
| if __name__ == "__main__": | |
| main() | |