Instructions to use Intel/NeuroPrompts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/NeuroPrompts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Intel/NeuroPrompts")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Intel/NeuroPrompts") model = AutoModelForCausalLM.from_pretrained("Intel/NeuroPrompts") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Intel/NeuroPrompts with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Intel/NeuroPrompts" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Intel/NeuroPrompts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Intel/NeuroPrompts
- SGLang
How to use Intel/NeuroPrompts 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 "Intel/NeuroPrompts" \ --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": "Intel/NeuroPrompts", "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 "Intel/NeuroPrompts" \ --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": "Intel/NeuroPrompts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Intel/NeuroPrompts with Docker Model Runner:
docker model run hf.co/Intel/NeuroPrompts
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,7 +38,7 @@ sys.path.insert(0,neurologic_path)
|
|
| 38 |
from neurologic_pe import generate_neurologic
|
| 39 |
|
| 40 |
# Load the pre-trained model and tokenizer
|
| 41 |
-
model_name = "/
|
| 42 |
model_type = 'finetuned'
|
| 43 |
# model_type = 'ppo'
|
| 44 |
rand_seed = 1535471403
|
|
|
|
| 38 |
from neurologic_pe import generate_neurologic
|
| 39 |
|
| 40 |
# Load the pre-trained model and tokenizer
|
| 41 |
+
model_name = "Intel/NeuroPrompts"
|
| 42 |
model_type = 'finetuned'
|
| 43 |
# model_type = 'ppo'
|
| 44 |
rand_seed = 1535471403
|