Instructions to use jetskewur/ClimAdaptLM-II-policy-annotator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jetskewur/ClimAdaptLM-II-policy-annotator with Transformers:

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

pipe = pipeline("text-generation", model="jetskewur/ClimAdaptLM-II-policy-annotator")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jetskewur/ClimAdaptLM-II-policy-annotator")
model = AutoModelForCausalLM.from_pretrained("jetskewur/ClimAdaptLM-II-policy-annotator")
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 jetskewur/ClimAdaptLM-II-policy-annotator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jetskewur/ClimAdaptLM-II-policy-annotator

SGLang

How to use jetskewur/ClimAdaptLM-II-policy-annotator 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 "jetskewur/ClimAdaptLM-II-policy-annotator" \
    --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": "jetskewur/ClimAdaptLM-II-policy-annotator",
		"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 "jetskewur/ClimAdaptLM-II-policy-annotator" \
        --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": "jetskewur/ClimAdaptLM-II-policy-annotator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jetskewur/ClimAdaptLM-II-policy-annotator with Docker Model Runner:
```
docker model run hf.co/jetskewur/ClimAdaptLM-II-policy-annotator
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

ClimAdaptLM-II-policy-annotator

This model is a fine-tuned version of Qwen/Qwen3-0.6B on a dataset of climate change adaptation policy text blocks (input) and structured arrays of JSON objects of adaptation policy goals, instruments, and outputs.

Model Description

This model extracts climate change adaptation policy elements from (adaptation-relevant) text chunks. When providing it the instruction 'Identify all climate change adaptation goals, instruments, and outputs in below text chunk' together with the input chunk, it returns JSON objects containing verbatim substrings from the chunk representing an adaptation policy element, together with the corresponding type (goal, instrument, or output).

Input format

This model is fine-tuned on adaptation-relevant input text chunks (pre-classified by distilroberta-base-climate-adaptation-detector) that with an average of 3,158 characters and 10 paragraphs per chunk.

Fine-tuning took place with in chat template style, with the instruction provided as system message and the input text as user message.