Instructions to use Xtra-Computing/XtraGPT-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xtra-Computing/XtraGPT-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="Xtra-Computing/XtraGPT-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("Xtra-Computing/XtraGPT-1.5B")
model = AutoModelForCausalLM.from_pretrained("Xtra-Computing/XtraGPT-1.5B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xtra-Computing/XtraGPT-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xtra-Computing/XtraGPT-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xtra-Computing/XtraGPT-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Xtra-Computing/XtraGPT-1.5B

SGLang

How to use Xtra-Computing/XtraGPT-1.5B 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 "Xtra-Computing/XtraGPT-1.5B" \
    --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": "Xtra-Computing/XtraGPT-1.5B",
		"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 "Xtra-Computing/XtraGPT-1.5B" \
        --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": "Xtra-Computing/XtraGPT-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Xtra-Computing/XtraGPT-1.5B with Docker Model Runner:
```
docker model run hf.co/Xtra-Computing/XtraGPT-1.5B
```

nuojohnchen commited on May 19, 2025

Commit

a930acc

verified ·

1 Parent(s): f15d527

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -57

README.md CHANGED Viewed

@@ -1,63 +1,24 @@
 ---
-library_name: transformers
 license: other
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 tags:
-- llama-factory
-- full
-- generated_from_trainer
-model-index:
-- name: Qwen2.5-1.5B-Instruct-all-new
-  results: []
 ---
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-# Qwen2.5-1.5B-Instruct-all-new
-This model is a fine-tuned version of [/ssd1/models/Qwen2.5-1.5B-Instruct/](https://huggingface.co//ssd1/models/Qwen2.5-1.5B-Instruct/) on the papertrain dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5940
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
-- total_eval_batch_size: 4
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2.0
-### Training results
-### Framework versions
-- Transformers 4.48.3
-- Pytorch 2.5.1+cu124
-- Datasets 3.1.0
-- Tokenizers 0.21.0

 ---
 license: other
+license_name: mg0-2.0
+license_link: https://github.com/Xtra-Computing/ModelGo/blob/main/MG_licenses/V2/MG0-2.0.txt
+language:
+- en
+pipeline_tag: text-generation
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 tags:
+- chat
+library_name: transformers
 ---
+```
+@misc{chen2025xtragpt,
+      title={XtraGPT: LLMs for Human-AI Collaboration on Controllable Academic Paper Revision},
+      author={Nuo Chen and Andre Lin HuiKai and Jiaying Wu and Junyi Hou and Zining Zhang and Qian Wang and Xidong Wang and Bingsheng He},
+      year={2025},
+      eprint={2505.11336},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.11336},
+}
+```