Instructions to use eci-io/climategpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eci-io/climategpt-7b with Transformers:

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

pipe = pipeline("text-generation", model="eci-io/climategpt-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eci-io/climategpt-7b")
model = AutoModelForCausalLM.from_pretrained("eci-io/climategpt-7b", device_map="auto")
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 Settings

vLLM

How to use eci-io/climategpt-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eci-io/climategpt-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eci-io/climategpt-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eci-io/climategpt-7b

SGLang

How to use eci-io/climategpt-7b 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 "eci-io/climategpt-7b" \
    --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": "eci-io/climategpt-7b",
		"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 "eci-io/climategpt-7b" \
        --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": "eci-io/climategpt-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eci-io/climategpt-7b with Docker Model Runner:
```
docker model run hf.co/eci-io/climategpt-7b
```

Request: Add HVAC Energy Efficiency Dataset to ClimateGPT Collection

by powertronglobal - opened Jan 4

Discussion

powertronglobal

Jan 4

Hello ClimateGPT team,

I'd like to request consideration of our dataset for your ClimateGPT collection:

Dataset: powertronglobal/powertron-global-permafrost-corpus

What it contains:

1,452 training chunks (~1M tokens) of PE-certified HVAC efficiency data
254 field measurements from 15 years of real-world installations
Before/after energy efficiency measurements (kW/ton, COP, EER)
Data from 6 independent labs including UL, NSF, and university validation

Climate relevance:

Documents 12.3 million kWh of energy savings
~8,700 metric tons CO2 avoided (documented)
Extrapolated potential: 1.71 million tonnes CO2/year at scale
Supports building energy efficiency research and climate tech AI

License: Explicitly licensed for AI/ML training

The dataset fills a gap in climate AI - real-world, PE-certified HVAC efficiency measurements rather than simulated data.

Would love to be considered for inclusion in your climate-focused collection.

Best regards,
Powertron Global

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment