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

Libraries

How to use Astrodevil/MyGemmaNPC with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Astrodevil/MyGemmaNPC")
model = AutoModelForCausalLM.from_pretrained("Astrodevil/MyGemmaNPC")
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

vLLM

How to use Astrodevil/MyGemmaNPC with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Astrodevil/MyGemmaNPC

SGLang

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

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

Astrodevil commited on Aug 16, 2025

Commit

8a190c9

verified ·

1 Parent(s): ce43264

Model save

Browse files

Files changed (3) hide show

generation_config.json +11 -0
model.safetensors +1 -1
runs/Aug16_18-30-13_16244f9740de/events.out.tfevents.1755369044.16244f9740de.1786.0 +2 -2

generation_config.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.55.1"
+}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1acad6d2de897471e321405d8abbb9a4fccda04642fcc3d98c421c37a432d1
 size 536223056

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b10557428c98c0639986a03e71013efb7cdb38b40983d9048aa485cef784e3c
 size 536223056

runs/Aug16_18-30-13_16244f9740de/events.out.tfevents.1755369044.16244f9740de.1786.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd27fc8b37d59052fb5387564ab82632200d498ed81e0785248b16df78240d0
-size 16220

 version https://git-lfs.github.com/spec/v1
+oid sha256:5bcc9f906aec315ee7cbaf7a38467d8ce50f7c8bfa2c8d45917428c1fd5bc913
+size 16568