Any-to-Any
MLX
Safetensors
gemma4
mlx-vlm
rlcd
multimodal
classification
parallel-inference
image-text-to-text
audio
video
4-bit precision
Instructions to use larkooo/gemma-e2b-rlcd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use larkooo/gemma-e2b-rlcd with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-e2b-rlcd larkooo/gemma-e2b-rlcd
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download examples/text-result.json from larkooo/gemma-e2b-rlcd: direct link, hf CLI and curl.
- Browser
- Download file 2.17 kB
-
https://huggingface.co/larkooo/gemma-e2b-rlcd/resolve/main/examples/text-result.json
- Command line
-
hf download hf://larkooo/gemma-e2b-rlcd/examples/text-result.json
-
curl -L -o text-result.json https://huggingface.co/larkooo/gemma-e2b-rlcd/resolve/main/examples/text-result.json
2.17 kB
| { | |
| "answers": { | |
| "animal": { | |
| "calibration_status": "unvalidated", | |
| "temperature": 1.0, | |
| "probability_source": "restricted_next_token_logits", | |
| "diagnostics": { | |
| "logits": { | |
| "cat": 14.711406707763672, | |
| "dog": -7.430335521697998, | |
| "other": -5.548311233520508 | |
| }, | |
| "allowed_token_mass": 0.9999990463256836, | |
| "input_tokens": 164 | |
| }, | |
| "confidence": 0.9999999641376001, | |
| "confidence_definition": "one_minus_normalized_entropy", | |
| "probabilities": { | |
| "cat": 0.9999999981682133, | |
| "dog": 2.4208257443645767e-10, | |
| "other": 1.5897040929196268e-09 | |
| }, | |
| "type": "choice", | |
| "choice": "cat", | |
| "selected_probability": 0.9999999981682133 | |
| }, | |
| "presence": { | |
| "calibration_status": "unvalidated", | |
| "temperature": 1.0, | |
| "probability_source": "restricted_next_token_logits", | |
| "type": "independent", | |
| "probabilities": { | |
| "cat": 0.9784876284221362, | |
| "dog": 9.911270087838716e-09 | |
| }, | |
| "diagnostics": { | |
| "cat": { | |
| "logits": { | |
| "yes": 10.465391159057617, | |
| "no": 6.648011207580566 | |
| }, | |
| "allowed_token_mass": 0.999992311000824, | |
| "input_tokens": 158 | |
| }, | |
| "dog": { | |
| "logits": { | |
| "yes": -0.7675755023956299, | |
| "no": 17.662017822265625 | |
| }, | |
| "allowed_token_mass": 0.9999980330467224, | |
| "input_tokens": 158 | |
| } | |
| } | |
| } | |
| }, | |
| "model": "models/gemma-4-e2b-it-4bit", | |
| "load_seconds": 2.818324833002407, | |
| "decision_seconds": 0.5153297919896431, | |
| "execution": { | |
| "execution": "shared_prefix_gpu_batched_branches", | |
| "prefix_prefills": 1, | |
| "prefix_tokens": 50, | |
| "question_suffix_tokens": [ | |
| 114, | |
| 108, | |
| 108 | |
| ], | |
| "preprocess_seconds": 0.039328291022684425, | |
| "prefill_seconds": 0.09224108399939723, | |
| "kv_storage": "replicated_per_batch_row", | |
| "compute_dtype": "float32", | |
| "branch_batch_sizes": [ | |
| 3 | |
| ], | |
| "branch_seconds": 0.38361333298962563 | |
| }, | |
| "video_sampling_fps": null, | |
| "video_soundtrack": null | |
| } | |