Instructions to use IJAS/gemma270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IJAS/gemma270m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IJAS/gemma270m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IJAS/gemma270m") model = AutoModelForCausalLM.from_pretrained("IJAS/gemma270m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IJAS/gemma270m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IJAS/gemma270m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IJAS/gemma270m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IJAS/gemma270m
- SGLang
How to use IJAS/gemma270m 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 "IJAS/gemma270m" \ --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": "IJAS/gemma270m", "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 "IJAS/gemma270m" \ --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": "IJAS/gemma270m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use IJAS/gemma270m with Docker Model Runner:
docker model run hf.co/IJAS/gemma270m
Download config.json from IJAS/gemma270m: direct link, hf CLI and curl.
- Browser
- Download file 1.57 kB
-
https://huggingface.co/IJAS/gemma270m/resolve/main/config.json
- Command line
-
hf download hf://IJAS/gemma270m/config.json
-
curl -L -o config.json https://huggingface.co/IJAS/gemma270m/resolve/main/config.json
1.57 kB
| { | |
| "_sliding_window_pattern": 6, | |
| "architectures": [ | |
| "Gemma3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "torch_dtype": "float16", | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 640, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "model_name": "unsloth/gemma-3-270m-unsloth-bnb-4bit", | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 512, | |
| "unsloth_fixed": true, | |
| "unsloth_version": "2026.8.9", | |
| "use_bidirectional_attention": false, | |
| "use_cache": false, | |
| "vocab_size": 262144 | |
| } |