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
| from __future__ import annotations | |
| from dataclasses import dataclass | |
| from typing import Any, Dict, Optional | |
| import torch | |
| from .shared_model import SharedBackboneAdapter, get_shared_adapter, register_shared_model | |
| class SharedSystems: | |
| adapter: SharedBackboneAdapter | |
| consciousness: Optional[Any] = None | |
| agi_memory: Optional[Any] = None | |
| errors: Optional[Dict[str, str]] = None | |
| def initialize_shared_systems( | |
| model, | |
| tokenizer=None, | |
| *, | |
| enable_consciousness: bool = True, | |
| enable_agi_memory: bool = True, | |
| ) -> SharedSystems: | |
| adapter = register_shared_model(model, tokenizer) | |
| errors: Dict[str, str] = {} | |
| consciousness = None | |
| agi_memory = None | |
| if enable_consciousness: | |
| try: | |
| from ConsciousnessSystem.config import ConsciousnessSystemConfig | |
| from ConsciousnessSystem.consciousness_system import ConsciousnessSystem | |
| cfg = ConsciousnessSystemConfig( | |
| device=str(adapter.device), | |
| hidden_dim=adapter.hidden_size, | |
| use_fp16=adapter.dtype in (torch.float16, torch.bfloat16), | |
| ) | |
| consciousness = ConsciousnessSystem(cfg, qwen_model=model) | |
| except Exception as exc: | |
| errors["consciousness"] = str(exc) | |
| if enable_agi_memory: | |
| try: | |
| from agi_memory.core import AGIMemoryConfig, AGIMemorySystem | |
| cfg = AGIMemoryConfig( | |
| device=adapter.device, | |
| use_fp16=adapter.dtype in (torch.float16, torch.bfloat16), | |
| disable_vae_compression=True, | |
| enable_rag=False, | |
| enable_dynamic_action=False, | |
| enable_neuro_fusion=False, | |
| enable_memory_optimization=False, | |
| ) | |
| agi_memory = AGIMemorySystem(cfg) | |
| except Exception as exc: | |
| errors["agi_memory"] = str(exc) | |
| return SharedSystems(adapter=adapter, consciousness=consciousness, agi_memory=agi_memory, errors=errors) | |