Instructions to use AuraWorxAI/weather-llm-initial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AuraWorxAI/weather-llm-initial with Transformers:

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

pipe = pipeline("text-generation", model="AuraWorxAI/weather-llm-initial")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AuraWorxAI/weather-llm-initial")
model = AutoModelForCausalLM.from_pretrained("AuraWorxAI/weather-llm-initial", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AuraWorxAI/weather-llm-initial with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AuraWorxAI/weather-llm-initial

SGLang

How to use AuraWorxAI/weather-llm-initial 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 "AuraWorxAI/weather-llm-initial" \
    --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": "AuraWorxAI/weather-llm-initial",
		"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 "AuraWorxAI/weather-llm-initial" \
        --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": "AuraWorxAI/weather-llm-initial",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AuraWorxAI/weather-llm-initial with Docker Model Runner:
```
docker model run hf.co/AuraWorxAI/weather-llm-initial
```

weather-llm-initial / scripts /preprocess_wiki.py

NagacharanVemula

Initial code-first model repo publish.

78dea75 4 months ago

Raw

History Blame Contribute Delete

1.48 kB

	#!/usr/bin/env python3
	"""Stream English Wikipedia articles into chunked JSONL (Hugging Face `datasets`)."""

	from __future__ import annotations

	import argparse
	import sys
	from pathlib import Path

	ROOT = Path(__file__).resolve().parents[1]
	sys.path.insert(0, str(ROOT / "src"))

	from tqdm import tqdm

	from weather_llm.config_loader import load_yaml, repo_root_from
	from weather_llm.data.jsonl_utils import write_jsonl
	from weather_llm.data.wiki import wikipedia_to_chunks


	def main() -> int:
	ap = argparse.ArgumentParser()
	ap.add_argument("--config", type=Path, default=None)
	args = ap.parse_args()
	root = repo_root_from(ROOT)
	cfg_path = args.config or (root / "configs/data_default.yaml")
	cfg = load_yaml(cfg_path)
	wiki = cfg["wikipedia"]
	paths = cfg["paths"]
	out_path = root / paths["processed"] / "wikipedia.jsonl"

	stream = wikipedia_to_chunks(
	dataset_name=str(wiki["dataset_name"]),
	dataset_config=str(wiki["dataset_config"]),
	max_articles=int(wiki["max_articles"]),
	min_article_chars=int(wiki["min_article_chars"]),
	chunk_target_chars=int(wiki["chunk_target_chars"]),
	chunk_overlap_chars=int(wiki["chunk_overlap_chars"]),
	)
	rows = []
	for row in tqdm(stream, desc="wiki chunks"):
	rows.append(row)
	write_jsonl(out_path, iter(rows))
	print("Wrote", len(rows), "chunks to", out_path)
	return 0


	if __name__ == "__main__":
	raise SystemExit(main())