Instructions to use mtaku3/XtraGPT-14B-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mtaku3/XtraGPT-14B-W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="mtaku3/XtraGPT-14B-W4A16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mtaku3/XtraGPT-14B-W4A16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("mtaku3/XtraGPT-14B-W4A16", trust_remote_code=True, 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 mtaku3/XtraGPT-14B-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mtaku3/XtraGPT-14B-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mtaku3/XtraGPT-14B-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mtaku3/XtraGPT-14B-W4A16

SGLang

How to use mtaku3/XtraGPT-14B-W4A16 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 "mtaku3/XtraGPT-14B-W4A16" \
    --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": "mtaku3/XtraGPT-14B-W4A16",
		"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 "mtaku3/XtraGPT-14B-W4A16" \
        --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": "mtaku3/XtraGPT-14B-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mtaku3/XtraGPT-14B-W4A16 with Docker Model Runner:
```
docker model run hf.co/mtaku3/XtraGPT-14B-W4A16
```

XtraGPT-14B-W4A16

This is an AWQ W4A16 quantization of Xtra-Computing/XtraGPT-14B. It is intended for context-aware academic-paper revision and preserves the original tokenizer and chat template.

Quantization

Algorithm: Activation-aware Weight Quantization (AWQ)
Format: compressed-tensors
Weights: asymmetric INT4
Activations: 16-bit
Group size: 128
Quantized modules: Linear, excluding lm_head
Calibration: 128 samples from Xtra-Computing/ReviseQA, maximum sequence length 2048
Source revision: 01dd781fea28a43bb36a0d297ee8181e849fb10c
Calibration dataset revision: 4826925f33d825be0d54ca7c5618c032d55ea337

The calibration inputs keep both the beginning of each paper prompt and the final revision question/answer when a sample exceeds the sequence limit.

Usage with vLLM

vllm serve REPO_ID \
  --served-model-name xtragpt \
  --max-model-len 16384 \
  --gpu-memory-utilization 0.95

Use the <PAPER_CONTENT>, <SELECTED_CONTENT>, and <QUESTION> prompt tags shown in the base model card.

Build environment

torch==2.13.0
transformers==5.14.1
llmcompressor==0.13.0
compressed-tensors==0.18.0
datasets==5.0.1
huggingface-hub==1.28.0

Evaluation

A short generation smoke test was run during quantization unless explicitly disabled. No benchmark result is claimed here; compare the quantized checkpoint with the BF16 source on a held-out ReviseQA subset before production use.

License and attribution

The source model is released under the ModelGo Zero License 2.0 (MG0-2.0). See the base model card and license text.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

I32

BF16

Model tree for mtaku3/XtraGPT-14B-W4A16

Base model

microsoft/phi-4

Finetuned

Xtra-Computing/XtraGPT-14B

Quantized

(2)

this model