Download config.json from FluidInference/embeddinggemma-2-coreml: direct link, hf CLI and curl.
- Browser
- Download file 2.85 kB
-
https://huggingface.co/FluidInference/embeddinggemma-2-coreml/resolve/main/config.json
- Command line
-
hf download hf://FluidInference/embeddinggemma-2-coreml/config.json
-
curl -L -o config.json https://huggingface.co/FluidInference/embeddinggemma-2-coreml/resolve/main/config.json
2.85 kB
| { | |
| "base_model": "google/embeddinggemma-2", | |
| "format": "coreml", | |
| "modality": [ | |
| "text", | |
| "audio", | |
| "image" | |
| ], | |
| "precision": "fp16", | |
| "hidden_size": 512, | |
| "embedding_dim": 768, | |
| "matryoshka_dims": [ | |
| 768, | |
| 512, | |
| 256, | |
| 128 | |
| ], | |
| "embed_scale": 22.627417, | |
| "token_table": { | |
| "file": "embeddings.bf16", | |
| "dtype": "bfloat16", | |
| "shape": [ | |
| 262144, | |
| 512 | |
| ] | |
| }, | |
| "functions": { | |
| "embed_32": { | |
| "tokens": 32 | |
| }, | |
| "embed_48": { | |
| "tokens": 48 | |
| }, | |
| "embed_64": { | |
| "tokens": 64 | |
| }, | |
| "embed_128": { | |
| "tokens": 128 | |
| }, | |
| "embed_256": { | |
| "tokens": 256 | |
| }, | |
| "embed_512": { | |
| "tokens": 512 | |
| }, | |
| "pack_256": { | |
| "tokens": 256, | |
| "slots": 8 | |
| } | |
| }, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "pad_token_id": 0, | |
| "prompts": { | |
| "document": "title: none | text: ", | |
| "search_query": "task: search result | query: ", | |
| "question_answering": "task: question answering | query: ", | |
| "fact_checking": "task: fact checking | query: ", | |
| "code_retrieval": "task: code retrieval | query: ", | |
| "classification": "task: classification | query: ", | |
| "clustering": "task: clustering | query: ", | |
| "sentence_similarity": "task: sentence similarity | query: " | |
| }, | |
| "audio": { | |
| "package": "EmbeddingGemma2Audio.mlpackage", | |
| "compute_units": "cpuAndGPU", | |
| "precision": "fp16", | |
| "sample_rate": 16000, | |
| "window_seconds": 10, | |
| "waveform_samples": 160160, | |
| "left_pad_samples": 160, | |
| "frames": 1000, | |
| "frame_valid_if": "i * 160 + 321 <= 160 + audio_samples", | |
| "tokens_per_window": 250, | |
| "token_ms": 40, | |
| "boa_token_id": 256000, | |
| "eoa_token_id": 258883, | |
| "text_sequence": "<bos> <|audio> [audio tokens] <audio|> <eos> -> embed_256" | |
| }, | |
| "vision": { | |
| "package": "EmbeddingGemma2Vision.mlpackage", | |
| "compute_units": "cpuAndGPU", | |
| "precision": "fp16", | |
| "functions": { | |
| "vision_70": { | |
| "tokens": 70, | |
| "patches": 630 | |
| }, | |
| "vision_140": { | |
| "tokens": 140, | |
| "patches": 1260 | |
| }, | |
| "vision_280": { | |
| "tokens": 280, | |
| "patches": 2520 | |
| } | |
| }, | |
| "patch_size": 16, | |
| "pooling_kernel": 3, | |
| "resize": "aspect-preserving, bicubic + antialias, sides multiple of 48 px, at most 9 x tokens patches", | |
| "pixel_scale": "RGB / 255 (the model applies 2x - 1)", | |
| "patch_layout": "row-major patches, each [16 rows][16 cols][RGB]", | |
| "position_table": { | |
| "file": "position_embeddings.f16", | |
| "dtype": "float16", | |
| "shape": [ | |
| 2, | |
| 1024, | |
| 768 | |
| ], | |
| "use": "table[0][x] + table[1][y] per patch, zero for padding" | |
| }, | |
| "boi_token_id": 255999, | |
| "eoi_token_id": 258882, | |
| "text_sequence": "<bos> <|image> [image tokens] <image|> <eos> -> smallest embed_S that fits" | |
| } | |
| } |