Instructions to use huseyincavus/tiny-gemma3-text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huseyincavus/tiny-gemma3-text with Transformers:

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

pipe = pipeline("text-generation", model="huseyincavus/tiny-gemma3-text")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huseyincavus/tiny-gemma3-text")
model = AutoModelForCausalLM.from_pretrained("huseyincavus/tiny-gemma3-text")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huseyincavus/tiny-gemma3-text with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huseyincavus/tiny-gemma3-text"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huseyincavus/tiny-gemma3-text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huseyincavus/tiny-gemma3-text

SGLang

How to use huseyincavus/tiny-gemma3-text 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 "huseyincavus/tiny-gemma3-text" \
    --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": "huseyincavus/tiny-gemma3-text",
		"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 "huseyincavus/tiny-gemma3-text" \
        --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": "huseyincavus/tiny-gemma3-text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use huseyincavus/tiny-gemma3-text with Docker Model Runner:
```
docker model run hf.co/huseyincavus/tiny-gemma3-text
```

tiny-gemma3-text / config.json

huseyincavus

Upload Gemma3ForCausalLM

2a43ca4 verified 6 days ago

Raw

History Blame Contribute Delete

1.22 kB

	{
	"_sliding_window_pattern": 6,
	"architectures": [
	"Gemma3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": null,
	"bos_token_id": 2,
	"cache_implementation": "hybrid",
	"dtype": "float32",
	"eos_token_id": [
	1,
	106
	],
	"final_logit_softcapping": null,
	"head_dim": 2,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 8,
	"initializer_range": 0.02,
	"intermediate_size": 16,
	"layer_types": [
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 128,
	"model_type": "gemma3_text",
	"num_attention_heads": 2,
	"num_hidden_layers": 4,
	"num_key_value_heads": 1,
	"pad_token_id": 0,
	"query_pre_attn_scalar": 2,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"sliding_attention": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"sliding_window": 2,
	"sliding_window_pattern": 1,
	"tie_word_embeddings": true,
	"transformers_version": "5.12.1",
	"use_bidirectional_attention": false,
	"use_cache": true,
	"vocab_size": 1024
	}