Instructions to use anonymousOwl/HydroAgent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anonymousOwl/HydroAgent with Transformers:

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

pipe = pipeline("text-generation", model="anonymousOwl/HydroAgent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anonymousOwl/HydroAgent")
model = AutoModelForCausalLM.from_pretrained("anonymousOwl/HydroAgent")
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

vLLM

How to use anonymousOwl/HydroAgent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anonymousOwl/HydroAgent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anonymousOwl/HydroAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anonymousOwl/HydroAgent

SGLang

How to use anonymousOwl/HydroAgent 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 "anonymousOwl/HydroAgent" \
    --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": "anonymousOwl/HydroAgent",
		"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 "anonymousOwl/HydroAgent" \
        --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": "anonymousOwl/HydroAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anonymousOwl/HydroAgent with Docker Model Runner:
```
docker model run hf.co/anonymousOwl/HydroAgent
```

anonymousOwl commited on 18 days ago

Commit

fe55589

verified ·

1 Parent(s): 84cdb6f

Update dataset link to anonymousOwl/HydroAgent-dataset

Browse files

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
 - crest
 - function-calling
 datasets:
-- chrimerss/hydro_cali_agent_example
 ---
 # HydroAgent — Qwen3-4B-Instruct fine-tuned for hydrologic model calibration
@@ -81,9 +81,12 @@ contain a clear flood event (rising + receding limbs, edge-buffered).
 | 06279500 | 40792 | 44.7585 | -108.1816 | 2018-06-13 → 2018-08-11 |
 | 07144100 |  3209 | 37.8831 |  -97.4245 | 2019-03-30 → 2019-05-28 |
-The full training dataset (MRMS clips, USGS observations, basin metadata,
-EF5 control template) is published as
-[**chrimerss/hydro_cali_agent_example**](https://huggingface.co/datasets/chrimerss/hydro_cali_agent_example).
 ## Reward

 - crest
 - function-calling
 datasets:
+- anonymousOwl/HydroAgent-dataset
 ---
 # HydroAgent — Qwen3-4B-Instruct fine-tuned for hydrologic model calibration
 | 06279500 | 40792 | 44.7585 | -108.1816 | 2018-06-13 → 2018-08-11 |
 | 07144100 |  3209 | 37.8831 |  -97.4245 | 2019-03-30 → 2019-05-28 |
+The full training dataset — CONUS terrain rasters, per-gage MRMS hourly
+precipitation clips, USGS hourly streamflow observations, daily PET, the
+EF5 control template, and the 73 GPT-4o calibration trajectories that seed
+the SFT phase — is published as
+[**anonymousOwl/HydroAgent-dataset**](https://huggingface.co/datasets/anonymousOwl/HydroAgent-dataset).
+See that repo's README for the per-folder layout and provenance.
 ## Reward