Instructions to use nikimori/gemma-4-e2b-4bit-slim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nikimori/gemma-4-e2b-4bit-slim with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("nikimori/gemma-4-e2b-4bit-slim") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use nikimori/gemma-4-e2b-4bit-slim with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "nikimori/gemma-4-e2b-4bit-slim" --prompt "Once upon a time"
- Atomic Chat
Download processor_config.json from nikimori/gemma-4-e2b-4bit-slim: direct link, hf CLI and curl.
- Browser
- Download file 902 Bytes
-
https://huggingface.co/nikimori/gemma-4-e2b-4bit-slim/resolve/main/processor_config.json
- Command line
-
hf download hf://nikimori/gemma-4-e2b-4bit-slim/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/nikimori/gemma-4-e2b-4bit-slim/resolve/main/processor_config.json
902 Bytes
| { | |
| "audio_seq_length": 750, | |
| "image_processor": { | |
| "do_convert_rgb": true, | |
| "do_normalize": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "image_processor_type": "Gemma4ImageProcessor", | |
| "image_seq_length": 280, | |
| "image_std": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "max_soft_tokens": 280, | |
| "patch_size": 16, | |
| "pooling_kernel_size": 3, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| }, | |
| "image_seq_length": 280, | |
| "processor_class": "Gemma4Processor", | |
| "feature_extractor": { | |
| "feature_extractor_type": "Gemma4AudioFeatureExtractor", | |
| "sampling_rate": 16000, | |
| "num_mel_filters": 128, | |
| "fft_length": 512, | |
| "hop_length": 160, | |
| "chunk_duration": 8.0, | |
| "overlap_duration": 1.0 | |
| }, | |
| "audio_ms_per_token": 40 | |
| } |