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
```

ringoreality commited on Dec 1, 2023

Commit

38b94d1

1 Parent(s): 6de3fd0

Create README.md

Browse files

Files changed (1) hide show

README.md +39 -0

README.md ADDED Viewed

	@@ -0,0 +1,39 @@

+# Model Card for climategpt/climategpt-7b-fsc
+- This model is the 7B parameter from-scratch climate ("fsc") variant of the ClimateGPT model release.
+## Overview
+- **Developed by:** AppTek, Eqtylab, Erasmus AI
+- **Model type:** decoder-only Transformer
+- **Language(s) (NLP):** natively supported: English; supported via cascaded MT on web interface: Arabic, Bangla, Chinese (simplified), Dutch, Finnougoric, French, Germanic, Greek, Hebrew, Indonesian, Japenese, Korean, Lithuanian, Pashto, Persian, Portuguese, Russian, Spanish, Thai, Turkish, Vietnamese,
+- **License:** TO BE ADDED
+- **Repository:** https://huggingface.co/climategpt/climategpt-7b-fsc
+- **Paper:** TO BE ADDED
+- **Demo:** TO BE ADDED
+## Uses
+- This model is intended to be directly used as a question answering model that is specialized in the climate domain.
+- The model is aimed at providing useful feedback for decision makers, scientists and jounalists involved in climate discussions.
+- The model can also be used as a starting point for interested developers for further finetuning.
+- The model is NOT intended to be a general-purpose chatbot (although it has chat capabilities).
+- For the full system including cascaded MT, RAG, etc., we recommend the user to go to our demo website: TO BE ADDED.
+- For hands-on finetuning deployment and inference, we recommend the user to directly use the Huggingface helpers.
+- For in-depth model conversion and finetuning, we recommend the user to use https://github.com/epfLLM/Megatron-LLM/.
+- **Despite the efforts from the development team to elimite them, as every other chat-capable LLMs, this model may generate biased, offensive, inaccurate responses.**
+## How to Get Started with the Model
+After downloading the HF formatted model, the HF helpers should work out-of-the-box.
+It is also possible to evaluate the model with https://github.com/EleutherAI/lm-evaluation-harness by plugging in the model identifier ```--model_args pretrained=climategpt/climategpt-70b```.
+## Training
+- For pretraining, a 300B-token dataset with an emphasis on the climate domain is prepared and used.
+- For instruction finetuning, about 1.1B instruction-finetuning tokens (both in the climate domain but also general domain) are used.
+## Environmental Impact
+- **Hardware Type:** H100
+- **Hours used:** 30720 hrs
+- **Cloud Provider:** TO BE ADDED
+- **Compute Region:** TO BE ADDED
+- **Carbon Emitted:** TO BE ADDED
+## Citation
+**BibTeX:** TO BE ADDED