Instructions to use Ashmal/ClimateGPT13B_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ashmal/ClimateGPT13B_en with Transformers:

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

pipe = pipeline("text-generation", model="Ashmal/ClimateGPT13B_en")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ashmal/ClimateGPT13B_en")
model = AutoModelForCausalLM.from_pretrained("Ashmal/ClimateGPT13B_en", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ashmal/ClimateGPT13B_en with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ashmal/ClimateGPT13B_en"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashmal/ClimateGPT13B_en",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ashmal/ClimateGPT13B_en

SGLang

How to use Ashmal/ClimateGPT13B_en 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 "Ashmal/ClimateGPT13B_en" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashmal/ClimateGPT13B_en",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Ashmal/ClimateGPT13B_en" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashmal/ClimateGPT13B_en",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ashmal/ClimateGPT13B_en with Docker Model Runner:
```
docker model run hf.co/Ashmal/ClimateGPT13B_en
```

ClimateGPT13B_en

Commit History

Jun 11, 2025

22:51
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
6975310

Oct 23, 2023

13:31
Upload training_args.bin with huggingface_hub

Ashmal

afd52ab
13:30
Upload trainer_state.json with huggingface_hub

Ashmal

abb67b4
13:29
Upload tokenizer.model with huggingface_hub

Ashmal

5ed71d5
13:29
Upload tokenizer_config.json with huggingface_hub

Ashmal

9b88698
13:28
Upload special_tokens_map.json with huggingface_hub

Ashmal

3affe00
13:28
Upload generation_config.json with huggingface_hub

Ashmal

002692d
13:27
Upload config.json with huggingface_hub

Ashmal

cc8e513

Oct 21, 2023

11:12
Upload pytorch_model.bin with huggingface_hub

Ashmal

8e873a6

Oct 20, 2023

13:58
initial commit

Ashmal

4047c60

Commit History

Jun 11, 2025

Adding `safetensors` variant of this model⁠

Oct 23, 2023

Upload training_args.bin with huggingface_hub

Upload trainer_state.json with huggingface_hub

Upload tokenizer.model with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload special_tokens_map.json with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload config.json with huggingface_hub

Oct 21, 2023

Upload pytorch_model.bin with huggingface_hub

Oct 20, 2023

initial commit