Instructions to use nn-tech/MetalGPT-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nn-tech/MetalGPT-1 with Transformers:

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

pipe = pipeline("text-generation", model="nn-tech/MetalGPT-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nn-tech/MetalGPT-1")
model = AutoModelForCausalLM.from_pretrained("nn-tech/MetalGPT-1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nn-tech/MetalGPT-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nn-tech/MetalGPT-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nn-tech/MetalGPT-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nn-tech/MetalGPT-1

SGLang

How to use nn-tech/MetalGPT-1 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 "nn-tech/MetalGPT-1" \
    --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": "nn-tech/MetalGPT-1",
		"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 "nn-tech/MetalGPT-1" \
        --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": "nn-tech/MetalGPT-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nn-tech/MetalGPT-1 with Docker Model Runner:
```
docker model run hf.co/nn-tech/MetalGPT-1
```

preductor commited on Dec 4, 2025

Commit

ef89f0a

verified ·

1 Parent(s): 25dd07c

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +17 -3

README.md CHANGED Viewed

@@ -1,6 +1,20 @@
 ## Description
-**MetalGPT-1** is a model built upon the Qwen3-32b and incorporates both continual pre-training and supervised fine-tuning.
 ---
@@ -43,7 +57,7 @@ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 generated_ids = model.generate(
     **model_inputs,
-    max_new_tokens=1024,
 )
 # Обрезаем префикс промпта
@@ -132,7 +146,7 @@ sampling_params = SamplingParams(
     repetition_penalty=1.05,
     top_p=0.8,
     top_k=70,
-    max_tokens=512,
 )
 prompt = (

+---
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- mining
+- russian
+license: apache-2.0
+datasets:
+- nn-tech/Alloy-Bench
+language:
+- ru
+base_model: Qwen/Qwen3-32B
+---
 ## Description
+**MetalGPT-1** is a model built upon the Qwen/Qwen3-32B and incorporates both continual pre-training and supervised fine-tuning.
 ---
 generated_ids = model.generate(
     **model_inputs,
+    max_new_tokens=2048,
 )
 # Обрезаем префикс промпта
     repetition_penalty=1.05,
     top_p=0.8,
     top_k=70,
+    max_tokens=2048,
 )
 prompt = (