Text Generation
PEFT
Safetensors
Transformers
English
llama
lora
dpo
smollm2
trl
conversational
text-generation-inference
Instructions to use Subject-Emu-5259/NeuralAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Subject-Emu-5259/NeuralAI with PEFT:
Base model is not found.
- Transformers
How to use Subject-Emu-5259/NeuralAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Subject-Emu-5259/NeuralAI") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Subject-Emu-5259/NeuralAI") model = AutoModelForCausalLM.from_pretrained("Subject-Emu-5259/NeuralAI", 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 Subject-Emu-5259/NeuralAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Subject-Emu-5259/NeuralAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Subject-Emu-5259/NeuralAI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Subject-Emu-5259/NeuralAI
- SGLang
How to use Subject-Emu-5259/NeuralAI 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 "Subject-Emu-5259/NeuralAI" \ --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": "Subject-Emu-5259/NeuralAI", "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 "Subject-Emu-5259/NeuralAI" \ --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": "Subject-Emu-5259/NeuralAI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Subject-Emu-5259/NeuralAI with Docker Model Runner:
docker model run hf.co/Subject-Emu-5259/NeuralAI
| #!/usr/bin/env python3 | |
| """ | |
| NeuralAI β Hugging Face Pull Script | |
| Downloads model checkpoints, training data, and configs from the Hub. | |
| """ | |
| import os | |
| import sys | |
| from huggingface_hub import HfApi, snapshot_download | |
| REPO_ID = "Subject-Emu-5259/NeuralAI" | |
| LOCAL_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) | |
| def main(): | |
| api = HfApi() | |
| user = api.whoami(token=True) | |
| print(f"π Connected as: {user['name']}") | |
| print(f"π¦ Repo: {REPO_ID}") | |
| action = sys.argv[1] if len(sys.argv) > 1 else "all" | |
| if action == "model" or action == "all": | |
| print("\nπ₯ Pulling model adapter...") | |
| model_files = [ | |
| "adapter_config.json", | |
| "adapter_model.safetensors", | |
| "chat_template.jinja", | |
| "tokenizer.json", | |
| "tokenizer_config.json", | |
| "training_log.json", | |
| ] | |
| for f in model_files: | |
| try: | |
| api.hf_hub_download( | |
| repo_id=REPO_ID, | |
| filename=f, | |
| local_dir=os.path.join(LOCAL_DIR, "checkpoints", "v2_model"), | |
| local_dir_use_symlinks=False, | |
| token=True | |
| ) | |
| print(f" β {f}") | |
| except Exception as e: | |
| print(f" βοΈ {f} (not found on Hub)") | |
| if action == "data" or action == "all": | |
| print("\nπ₯ Pulling training data...") | |
| try: | |
| files = api.list_repo_files(REPO_ID, repo_type="model", token=True) | |
| data_files = [f for f in files if f.startswith("data/")] | |
| for f in data_files: | |
| local_path = os.path.join(LOCAL_DIR, f) | |
| os.makedirs(os.path.dirname(local_path), exist_ok=True) | |
| api.hf_hub_download( | |
| repo_id=REPO_ID, | |
| filename=f, | |
| local_dir=LOCAL_DIR, | |
| local_dir_use_symlinks=False, | |
| token=True | |
| ) | |
| print(f" β {f}") | |
| except Exception as e: | |
| print(f" β Error: {e}") | |
| if action == "scripts" or action == "all": | |
| print("\nπ₯ Pulling training scripts...") | |
| try: | |
| files = api.list_repo_files(REPO_ID, repo_type="model", token=True) | |
| for prefix in ["training/", "services/", "tools/"]: | |
| for f in [x for x in files if x.startswith(prefix)]: | |
| local_path = os.path.join(LOCAL_DIR, f) | |
| os.makedirs(os.path.dirname(local_path), exist_ok=True) | |
| api.hf_hub_download( | |
| repo_id=REPO_ID, | |
| filename=f, | |
| local_dir=LOCAL_DIR, | |
| local_dir_use_symlinks=False, | |
| token=True | |
| ) | |
| print(f" β {f}") | |
| except Exception as e: | |
| print(f" β Error: {e}") | |
| print(f"\n{'='*50}") | |
| print(f"β Pull complete! Files synced to {LOCAL_DIR}") | |
| print(f"{'='*50}") | |
| if __name__ == "__main__": | |
| main() | |