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

Libraries

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

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

pipe = pipeline("text-generation", model="eci-io/climategpt-7b-fsc")
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-fsc")
model = AutoModelForCausalLM.from_pretrained("eci-io/climategpt-7b-fsc", 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-fsc 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-fsc"
# 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-fsc",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

climategpt-7b-fsc / .integrity /bafkr4iesxpxpchttjusolg4z43aqi3kezantb2vreubu4la4y4inyfxn7m.node

tjbrunk

add integrity graph files

78ebcb4 verified over 2 years ago

Raw

History Blame Contribute Delete

1.01 kB

{"node":{"id":"urn:cid:bafkr4iesxpxpchttjusolg4z43aqi3kezantb2vreubu4la4y4inyfxn7m","properties":{"nodeType":"data","registeredBy":"did:key:zDnaep4gZ2eascVicXKfCzw82H52QLC59TfWtgKsJYJZX2qgX","dataRegistrationJcs":"urn:cid:baga6yaq6edd5r6onvaq62dc43l6fgjogisoxqk7s6smo4wh4nvc5232gwe6gq","timestamp":"2023-11-30T17:54:45Z"}},"enrichments":{"asset_hub":{"asset_id":263,"asset_name":"openbookqa: fs-7b-climate-c2 benchmark result","owning_project":"ECI_ClimateGPT","asset_description":"fs-7b-climate-c2 result and logs for openbookqa benchmark","asset_format":"folder","asset_type":"Benchmark_Result","asset_blob_type":"iroh-collection","source_location_url":"https://github.com/eqtylab/vcomp-results/tree/main/eval-harness/eqty-integrity-fs-7b-climate-c2-openbookqa-2023-11-30_17-51-56/output/","contact_info":"https://eqtylab.io","license":"Custom License - Refer to the official site for terms","license_link":"","registered_date":"2024-01-05T00:39:30.10536Z","last_modified_date":"2024-01-05T01:12:33.194822Z"}}}