Instructions to use uralstech/hAI-Spec-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uralstech/hAI-Spec-Merged with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="uralstech/hAI-Spec-Merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uralstech/hAI-Spec-Merged")
model = AutoModelForCausalLM.from_pretrained("uralstech/hAI-Spec-Merged")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use uralstech/hAI-Spec-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uralstech/hAI-Spec-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uralstech/hAI-Spec-Merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/uralstech/hAI-Spec-Merged

SGLang

How to use uralstech/hAI-Spec-Merged 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 "uralstech/hAI-Spec-Merged" \
    --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": "uralstech/hAI-Spec-Merged",
		"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 "uralstech/hAI-Spec-Merged" \
        --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": "uralstech/hAI-Spec-Merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use uralstech/hAI-Spec-Merged with Docker Model Runner:
```
docker model run hf.co/uralstech/hAI-Spec-Merged
```

hAI! Spec

This is the HuggingFace model repository for Nasa SpaceApps Challenge team hAI! Spec. You will find the hAI! Spec LLM here.

Our solution, named hAI! Spec, is a Language Learning Model (LLM) designed to optimize the management of technical standards within the aerospace industry. Trained on changes between historical and current versions of various standards, hAI! Spec uses a unique Section-By-Section training approach. This allows the model to provide accurate recommendations for improving document consistency, relevance, and accuracy, even down to the smallest grammatical detail in extensive documents like NASA standards.

Downloads last month: 6