Text Generation
Transformers
PyTorch
neuralquantum_nqlm
quantum
nlp
language-model
neural-quantum
hybrid-computing
custom_code
Instructions to use NeuralQuantum/nqlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NeuralQuantum/nqlm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NeuralQuantum/nqlm", trust_remote_code=True)# Load model directly from transformers import NeuralQuantumNQLM model = NeuralQuantumNQLM.from_pretrained("NeuralQuantum/nqlm", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use NeuralQuantum/nqlm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NeuralQuantum/nqlm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeuralQuantum/nqlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NeuralQuantum/nqlm
- SGLang
How to use NeuralQuantum/nqlm 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 "NeuralQuantum/nqlm" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeuralQuantum/nqlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "NeuralQuantum/nqlm" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeuralQuantum/nqlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NeuralQuantum/nqlm with Docker Model Runner:
docker model run hf.co/NeuralQuantum/nqlm
Add configuration_nqlm.py
Browse files- configuration_nqlm.py +58 -0
configuration_nqlm.py
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
NeuralQuantum NQLM Configuration for Hugging Face Transformers
|
| 3 |
+
"""
|
| 4 |
+
|
| 5 |
+
from transformers import PretrainedConfig
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
class NeuralQuantumNQLMConfig(PretrainedConfig):
|
| 9 |
+
"""Configuration class for NeuralQuantum NQLM model"""
|
| 10 |
+
|
| 11 |
+
model_type = "neuralquantum_nqlm"
|
| 12 |
+
|
| 13 |
+
def __init__(
|
| 14 |
+
self,
|
| 15 |
+
vocab_size=50257,
|
| 16 |
+
hidden_size=768,
|
| 17 |
+
num_attention_heads=12,
|
| 18 |
+
num_hidden_layers=12,
|
| 19 |
+
intermediate_size=3072,
|
| 20 |
+
hidden_act="gelu",
|
| 21 |
+
hidden_dropout_prob=0.1,
|
| 22 |
+
attention_probs_dropout_prob=0.1,
|
| 23 |
+
max_position_embeddings=512,
|
| 24 |
+
type_vocab_size=2,
|
| 25 |
+
initializer_range=0.02,
|
| 26 |
+
layer_norm_eps=1e-12,
|
| 27 |
+
use_cache=True,
|
| 28 |
+
quantum_enhancement=True,
|
| 29 |
+
quantum_layers=4,
|
| 30 |
+
quantum_circuit_depth=8,
|
| 31 |
+
quantum_optimization="vqe",
|
| 32 |
+
hybrid_mode=True,
|
| 33 |
+
torch_dtype="float16",
|
| 34 |
+
**kwargs
|
| 35 |
+
):
|
| 36 |
+
super().__init__(**kwargs)
|
| 37 |
+
|
| 38 |
+
self.vocab_size = vocab_size
|
| 39 |
+
self.hidden_size = hidden_size
|
| 40 |
+
self.num_attention_heads = num_attention_heads
|
| 41 |
+
self.num_hidden_layers = num_hidden_layers
|
| 42 |
+
self.intermediate_size = intermediate_size
|
| 43 |
+
self.hidden_act = hidden_act
|
| 44 |
+
self.hidden_dropout_prob = hidden_dropout_prob
|
| 45 |
+
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
| 46 |
+
self.max_position_embeddings = max_position_embeddings
|
| 47 |
+
self.type_vocab_size = type_vocab_size
|
| 48 |
+
self.initializer_range = initializer_range
|
| 49 |
+
self.layer_norm_eps = layer_norm_eps
|
| 50 |
+
self.use_cache = use_cache
|
| 51 |
+
|
| 52 |
+
# Quantum-specific parameters
|
| 53 |
+
self.quantum_enhancement = quantum_enhancement
|
| 54 |
+
self.quantum_layers = quantum_layers
|
| 55 |
+
self.quantum_circuit_depth = quantum_circuit_depth
|
| 56 |
+
self.quantum_optimization = quantum_optimization
|
| 57 |
+
self.hybrid_mode = hybrid_mode
|
| 58 |
+
self.torch_dtype = torch_dtype
|