Text Generation
Transformers
Safetensors
qwen2
coder
code
agent
conversational
text-generation-inference
Instructions to use AdminReal/NexusCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdminReal/NexusCoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdminReal/NexusCoder") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AdminReal/NexusCoder") model = AutoModelForCausalLM.from_pretrained("AdminReal/NexusCoder", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AdminReal/NexusCoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdminReal/NexusCoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminReal/NexusCoder", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AdminReal/NexusCoder
- SGLang
How to use AdminReal/NexusCoder 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 "AdminReal/NexusCoder" \ --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": "AdminReal/NexusCoder", "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 "AdminReal/NexusCoder" \ --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": "AdminReal/NexusCoder", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AdminReal/NexusCoder with Docker Model Runner:
docker model run hf.co/AdminReal/NexusCoder
| """ | |
| Script chat với Nexus Agent | |
| ============================= | |
| Chạy: python scripts/chat.py | |
| """ | |
| import sys | |
| import os | |
| sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) | |
| import torch | |
| from nexus.config import NexusConfig | |
| from nexus.model.nexus_coder import NexusCoderForCausalLM | |
| from nexus.tokenizer.tokenizer import NexusTokenizer | |
| from nexus.inference.generator import NexusGenerator | |
| from nexus.agent.agent import NexusAgent | |
| from nexus.training.dataset import AUTHOR_TRAINING_DATA | |
| def get_tiny_config() -> NexusConfig: | |
| """Tiny config cho demo chat.""" | |
| return NexusConfig( | |
| vocab_size=2000, | |
| hidden_size=256, | |
| num_hidden_layers=4, | |
| num_attention_heads=8, | |
| num_kv_heads=2, | |
| head_dim=32, | |
| intermediate_size=512, | |
| num_experts=4, | |
| num_active_experts=2, | |
| max_position_embeddings=512, | |
| ) | |
| def main(): | |
| print("=" * 60) | |
| print(" NEXUS CODER v0.1 - Chat Demo") | |
| print(" Tác giả: Hieu Louis") | |
| print(" Năm: 2026") | |
| print("=" * 60) | |
| # Init config (dùng tiny cho demo, vì full 10B cần GPU) | |
| config = get_tiny_config() | |
| print(f"\n📝 Cấu hình demo: hidden={config.hidden_size}, layers={config.num_hidden_layers}") | |
| # Tokenizer | |
| print("\n🔨 Đang huấn luyện tokenizer...") | |
| tokenizer = NexusTokenizer(vocab_size=config.vocab_size) | |
| corpus = [f"{d['system']} {d['user']} {d['assistant']}" for d in AUTHOR_TRAINING_DATA] | |
| tokenizer.train(corpus) | |
| print(f" ✓ {tokenizer.vocab_size} tokens") | |
| # Model | |
| print("\n🧠 Đang khởi tạo model...") | |
| model = NexusCoderForCausalLM(config) | |
| print(" ✓ Model ready (random weights - đây chỉ là demo kiến trúc)") | |
| # Generator | |
| generator = NexusGenerator( | |
| model=model, | |
| tokenizer=tokenizer, | |
| config=config, | |
| ) | |
| # Agent | |
| agent = NexusAgent( | |
| generator=generator, | |
| config=config, | |
| name="Nexus", | |
| personality="humorous", | |
| language="bilingual", | |
| ) | |
| # Print info | |
| agent._print_info() | |
| # Start chat | |
| agent.chat() | |
| if __name__ == "__main__": | |
| main() | |