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] hf download larkooo/gemma-e2b-rlcd --local-dir gemma-e2b-rlcd
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download reports/installed-cached-text.json from larkooo/gemma-e2b-rlcd: direct link, hf CLI and curl.
- Browser
- Download file 2.24 kB
-
https://huggingface.co/larkooo/gemma-e2b-rlcd/resolve/main/reports/installed-cached-text.json
- Command line
-
hf download hf://larkooo/gemma-e2b-rlcd/reports/installed-cached-text.json
-
curl -L -o installed-cached-text.json https://huggingface.co/larkooo/gemma-e2b-rlcd/resolve/main/reports/installed-cached-text.json
2.24 kB
| { | |
| "answers": { | |
| "animal": { | |
| "calibration_status": "unvalidated", | |
| "temperature": 1.0, | |
| "probability_source": "restricted_next_token_logits", | |
| "diagnostics": { | |
| "logits": { | |
| "cat": 14.71272087097168, | |
| "dog": -7.456348896026611, | |
| "other": -5.5611371994018555 | |
| }, | |
| "allowed_token_mass": 0.9999990463256836, | |
| "input_tokens": 164 | |
| }, | |
| "confidence": 0.9999999646809655, | |
| "confidence_definition": "one_minus_normalized_entropy", | |
| "probabilities": { | |
| "cat": 0.9999999981970598, | |
| "dog": 2.355566289369627e-10, | |
| "other": 1.5673836507448165e-09 | |
| }, | |
| "type": "choice", | |
| "choice": "cat", | |
| "selected_probability": 0.9999999981970598 | |
| }, | |
| "presence": { | |
| "calibration_status": "unvalidated", | |
| "temperature": 1.0, | |
| "probability_source": "restricted_next_token_logits", | |
| "type": "independent", | |
| "probabilities": { | |
| "cat": 0.9790092102982527, | |
| "dog": 9.754112398963197e-09 | |
| }, | |
| "diagnostics": { | |
| "cat": { | |
| "logits": { | |
| "yes": 10.473838806152344, | |
| "no": 6.631381511688232 | |
| }, | |
| "allowed_token_mass": 0.9999933242797852, | |
| "input_tokens": 158 | |
| }, | |
| "dog": { | |
| "logits": { | |
| "yes": -0.7610828280448914, | |
| "no": 17.684494018554688 | |
| }, | |
| "allowed_token_mass": 0.9999980330467224, | |
| "input_tokens": 158 | |
| } | |
| } | |
| } | |
| }, | |
| "model": "models/gemma-4-e2b-it-4bit", | |
| "load_seconds": 2.852635374991223, | |
| "decision_seconds": 0.33598891700967215, | |
| "execution": { | |
| "execution": "shared_prefix_gpu_batched_branches", | |
| "prefix_prefills": 1, | |
| "prefix_tokens": 50, | |
| "question_suffix_tokens": [ | |
| 114, | |
| 108, | |
| 108 | |
| ], | |
| "preprocess_seconds": 0.025576665997505188, | |
| "prefill_seconds": 0.10633495901129209, | |
| "kv_storage": "replicated_per_batch_row", | |
| "compute_dtype": "float32", | |
| "answer_mode": "gather", | |
| "branch_batch_sizes": [ | |
| 3 | |
| ], | |
| "answer_tail_tokens": [ | |
| 1 | |
| ], | |
| "branch_seconds": 0.20392720800009556 | |
| }, | |
| "video_sampling_fps": null, | |
| "video_soundtrack": null | |
| } | |