Instructions to use bumblebee-testing/tiny-random-Gemma3ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bumblebee-testing/tiny-random-Gemma3ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="bumblebee-testing/tiny-random-Gemma3ForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bumblebee-testing/tiny-random-Gemma3ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("bumblebee-testing/tiny-random-Gemma3ForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bumblebee-testing/tiny-random-Gemma3ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bumblebee-testing/tiny-random-Gemma3ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bumblebee-testing/tiny-random-Gemma3ForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bumblebee-testing/tiny-random-Gemma3ForCausalLM

SGLang

How to use bumblebee-testing/tiny-random-Gemma3ForCausalLM 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 "bumblebee-testing/tiny-random-Gemma3ForCausalLM" \
    --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": "bumblebee-testing/tiny-random-Gemma3ForCausalLM",
		"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 "bumblebee-testing/tiny-random-Gemma3ForCausalLM" \
        --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": "bumblebee-testing/tiny-random-Gemma3ForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bumblebee-testing/tiny-random-Gemma3ForCausalLM with Docker Model Runner:
```
docker model run hf.co/bumblebee-testing/tiny-random-Gemma3ForCausalLM
```

jonatanklosko commited on Dec 31, 2025

Commit

d280381

verified ·

1 Parent(s): e075e7c

Upload Gemma3ForCausalLM

Browse files

Files changed (2) hide show

config.json +2 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_sliding_window_pattern": 6,
   "architectures": [
     "Gemma3ForCausalLM"
   ],
@@ -34,6 +34,7 @@
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 128,
   "transformers_version": "4.57.0",
   "type_vocab_size": 16,
   "use_bidirectional_attention": false,

 {
+  "_sliding_window_pattern": 2,
   "architectures": [
     "Gemma3ForCausalLM"
   ],
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 128,
+  "sliding_window_pattern": 2,
   "transformers_version": "4.57.0",
   "type_vocab_size": 16,
   "use_bidirectional_attention": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d80df4c7423e5a75e37a82fa00d142f0bab2335e558ef40833b6b908b4bd9f
 size 954096

 version https://git-lfs.github.com/spec/v1
+oid sha256:fa2be5f46e1694a04e32cfabf63c3681843c54b94f305ddf594f1cd3d19734ed
 size 954096