Feature Extraction
GGUF
llama.cpp
embeddings
multimodal
vision
audio
image-feature-extraction
audio-feature-extraction
Instructions to use MirrorNeuronLab/embeddinggemma-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible embeddings server: llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible embeddings server: llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible embeddings server: ./build/bin/llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
- Llama new
- LM Studio
- Jan
- Ollama
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Ollama:
ollama run hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Docker Model Runner:
docker model run hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
- Lemonade
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.embeddinggemma-2-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download GGUF_AUDIT.json from MirrorNeuronLab/embeddinggemma-2-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 10.5 kB
-
https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/GGUF_AUDIT.json
- Command line
-
hf download hf://MirrorNeuronLab/embeddinggemma-2-GGUF/GGUF_AUDIT.json
-
curl -L -o GGUF_AUDIT.json https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/GGUF_AUDIT.json
10.5 kB
| { | |
| "passed": true, | |
| "preserved_metadata_fields": [ | |
| "gemma-embedding2.block_count", | |
| "gemma-embedding2.context_length", | |
| "gemma-embedding2.embedding_length", | |
| "gemma-embedding2.feed_forward_length", | |
| "gemma-embedding2.attention.head_count", | |
| "gemma-embedding2.attention.head_count_kv", | |
| "gemma-embedding2.rope.freq_base", | |
| "gemma-embedding2.rope.freq_base_swa", | |
| "gemma-embedding2.attention.layer_norm_rms_epsilon", | |
| "gemma-embedding2.attention.key_length", | |
| "gemma-embedding2.attention.value_length", | |
| "gemma-embedding2.attention.sliding_window", | |
| "gemma-embedding2.attention.shared_kv_layers", | |
| "gemma-embedding2.embedding_length_per_layer_input", | |
| "gemma-embedding2.attention.sliding_window_pattern", | |
| "gemma-embedding2.attention.key_length_swa", | |
| "gemma-embedding2.attention.value_length_swa", | |
| "gemma-embedding2.rope.dimension_count", | |
| "gemma-embedding2.rope.dimension_count_swa", | |
| "gemma-embedding2.embedding_length_out", | |
| "gemma-embedding2.attention.causal", | |
| "gemma-embedding2.pooling_type", | |
| "tokenizer.ggml.model", | |
| "tokenizer.ggml.tokens", | |
| "tokenizer.ggml.scores", | |
| "tokenizer.ggml.token_type", | |
| "tokenizer.ggml.merges", | |
| "tokenizer.ggml.bos_token_id", | |
| "tokenizer.ggml.eos_token_id", | |
| "tokenizer.ggml.unknown_token_id", | |
| "tokenizer.ggml.padding_token_id", | |
| "tokenizer.ggml.mask_token_id", | |
| "tokenizer.ggml.add_bos_token", | |
| "tokenizer.ggml.add_eos_token", | |
| "tokenizer.ggml.add_sep_token", | |
| "tokenizer.chat_template", | |
| "tokenizer.ggml.add_space_prefix" | |
| ], | |
| "tokenizer_tokens": 262144, | |
| "projection_tensor": { | |
| "name": "output.weight", | |
| "shape_ggml": [ | |
| 512, | |
| 768 | |
| ] | |
| }, | |
| "files": [ | |
| { | |
| "path": "work/embeddinggemma-2-BF16.gguf", | |
| "size_bytes": 557950176, | |
| "sha256": "68bae29d62fb8c7d23e98d21fd4662753ddd636e6b62b8a70dfe059a9844f216", | |
| "tensor_count": 413, | |
| "tensor_types": { | |
| "BF16": 219, | |
| "F32": 194 | |
| }, | |
| "tensor_prefixes": { | |
| "token_embd": 1, | |
| "output": 1, | |
| "blk": 408, | |
| "output_norm": 1, | |
| "per_layer_model_proj": 1, | |
| "per_layer_proj_norm": 1 | |
| }, | |
| "metadata": { | |
| "general.architecture": "gemma-embedding2", | |
| "general.type": "model", | |
| "general.name": "embeddinggemma-2", | |
| "general.size_label": "271M", | |
| "general.license": "apache-2.0", | |
| "general.tags": [ | |
| "embedding", | |
| "feature-extraction", | |
| "sentence-transformers", | |
| "multimodal-embedding", | |
| "multimodal", | |
| "vision", | |
| "audio", | |
| "video", | |
| "image-feature-extraction", | |
| "audio-feature-extraction", | |
| "video-feature-extraction", | |
| "sentence-similarity", | |
| "feature-extraction" | |
| ], | |
| "general.languages": [ | |
| "multilingual" | |
| ], | |
| "gemma-embedding2.block_count": 24, | |
| "gemma-embedding2.context_length": 262144, | |
| "gemma-embedding2.embedding_length": 512, | |
| "gemma-embedding2.feed_forward_length": 2048, | |
| "gemma-embedding2.attention.head_count": 4, | |
| "gemma-embedding2.attention.head_count_kv": [ | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1 | |
| ], | |
| "gemma-embedding2.rope.freq_base": 1000000.0, | |
| "gemma-embedding2.rope.freq_base_swa": 10000.0, | |
| "gemma-embedding2.attention.layer_norm_rms_epsilon": 9.999999974752427e-07, | |
| "gemma-embedding2.attention.key_length": 512, | |
| "gemma-embedding2.attention.value_length": 512, | |
| "general.file_type": 32, | |
| "gemma-embedding2.attention.sliding_window": 1024, | |
| "gemma-embedding2.attention.shared_kv_layers": 0, | |
| "gemma-embedding2.embedding_length_per_layer_input": 512, | |
| "gemma-embedding2.attention.sliding_window_pattern": [ | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false | |
| ], | |
| "gemma-embedding2.attention.key_length_swa": 256, | |
| "gemma-embedding2.attention.value_length_swa": 256, | |
| "gemma-embedding2.rope.dimension_count": 512, | |
| "gemma-embedding2.rope.dimension_count_swa": 256, | |
| "gemma-embedding2.embedding_length_out": 768, | |
| "gemma-embedding2.attention.causal": false, | |
| "gemma-embedding2.pooling_type": 1, | |
| "general.quantization_version": 2 | |
| } | |
| }, | |
| { | |
| "path": "release/embeddinggemma-2-Q4_K_M.gguf", | |
| "size_bytes": 181694688, | |
| "sha256": "d610afe26dd783739275646d51d4d85b4167820fd051600696d7a49e6f68609f", | |
| "tensor_count": 413, | |
| "tensor_types": { | |
| "Q6_K": 25, | |
| "F32": 194, | |
| "BF16": 1, | |
| "Q4_K": 193 | |
| }, | |
| "tensor_prefixes": { | |
| "output": 1, | |
| "output_norm": 1, | |
| "per_layer_model_proj": 1, | |
| "per_layer_proj_norm": 1, | |
| "token_embd": 1, | |
| "blk": 408 | |
| }, | |
| "metadata": { | |
| "general.architecture": "gemma-embedding2", | |
| "general.type": "model", | |
| "general.name": "embeddinggemma-2", | |
| "general.size_label": "271M", | |
| "general.license": "apache-2.0", | |
| "general.tags": [ | |
| "embedding", | |
| "feature-extraction", | |
| "sentence-transformers", | |
| "multimodal-embedding", | |
| "multimodal", | |
| "vision", | |
| "audio", | |
| "video", | |
| "image-feature-extraction", | |
| "audio-feature-extraction", | |
| "video-feature-extraction", | |
| "sentence-similarity", | |
| "feature-extraction" | |
| ], | |
| "general.languages": [ | |
| "multilingual" | |
| ], | |
| "gemma-embedding2.block_count": 24, | |
| "gemma-embedding2.context_length": 262144, | |
| "gemma-embedding2.embedding_length": 512, | |
| "gemma-embedding2.feed_forward_length": 2048, | |
| "gemma-embedding2.attention.head_count": 4, | |
| "gemma-embedding2.attention.head_count_kv": [ | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 1 | |
| ], | |
| "gemma-embedding2.rope.freq_base": 1000000.0, | |
| "gemma-embedding2.rope.freq_base_swa": 10000.0, | |
| "gemma-embedding2.attention.layer_norm_rms_epsilon": 9.999999974752427e-07, | |
| "gemma-embedding2.attention.key_length": 512, | |
| "gemma-embedding2.attention.value_length": 512, | |
| "gemma-embedding2.attention.sliding_window": 1024, | |
| "gemma-embedding2.attention.shared_kv_layers": 0, | |
| "gemma-embedding2.embedding_length_per_layer_input": 512, | |
| "gemma-embedding2.attention.sliding_window_pattern": [ | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false | |
| ], | |
| "gemma-embedding2.attention.key_length_swa": 256, | |
| "gemma-embedding2.attention.value_length_swa": 256, | |
| "gemma-embedding2.rope.dimension_count": 512, | |
| "gemma-embedding2.rope.dimension_count_swa": 256, | |
| "gemma-embedding2.embedding_length_out": 768, | |
| "gemma-embedding2.attention.causal": false, | |
| "gemma-embedding2.pooling_type": 1, | |
| "general.quantization_version": 2, | |
| "general.file_type": 15 | |
| } | |
| }, | |
| { | |
| "path": "release/mmproj-embeddinggemma-2-Q8_0.gguf", | |
| "size_bytes": 554821056, | |
| "sha256": "0531309472a6bc6f4b146c3736eee7795ec9db1903c25490d3c937490cef6dd8", | |
| "tensor_count": 963, | |
| "tensor_types": { | |
| "F32": 716, | |
| "Q8_0": 247 | |
| }, | |
| "tensor_prefixes": { | |
| "a": 751, | |
| "mm": 2, | |
| "v": 210 | |
| }, | |
| "metadata": { | |
| "general.architecture": "clip", | |
| "general.type": "mmproj", | |
| "general.name": "embeddinggemma-2", | |
| "general.size_label": "473M", | |
| "general.license": "apache-2.0", | |
| "general.tags": [ | |
| "embedding", | |
| "feature-extraction", | |
| "sentence-transformers", | |
| "multimodal-embedding", | |
| "multimodal", | |
| "vision", | |
| "audio", | |
| "video", | |
| "image-feature-extraction", | |
| "audio-feature-extraction", | |
| "video-feature-extraction", | |
| "sentence-similarity", | |
| "feature-extraction" | |
| ], | |
| "general.languages": [ | |
| "multilingual" | |
| ], | |
| "general.file_type": 7, | |
| "clip.has_vision_encoder": true, | |
| "clip.vision.projection_dim": 512, | |
| "clip.vision.image_size": 224, | |
| "clip.vision.patch_size": 16, | |
| "clip.vision.embedding_length": 768, | |
| "clip.vision.feed_forward_length": 3072, | |
| "clip.vision.block_count": 16, | |
| "clip.vision.attention.head_count": 12, | |
| "clip.vision.image_mean": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "clip.vision.image_std": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "clip.has_audio_encoder": true, | |
| "clip.audio.projection_dim": 512, | |
| "clip.audio.embedding_length": 1024, | |
| "clip.audio.feed_forward_length": 4096, | |
| "clip.audio.block_count": 12, | |
| "clip.audio.attention.head_count": 8, | |
| "clip.vision.projector_type": "gemma4v", | |
| "clip.vision.attention.layer_norm_epsilon": 9.999999974752427e-07, | |
| "clip.use_gelu": true, | |
| "clip.audio.projector_type": "gemma4a", | |
| "clip.audio.num_mel_bins": 128, | |
| "clip.audio.attention.layer_norm_epsilon": 9.999999974752427e-07, | |
| "general.quantization_version": 2 | |
| } | |
| } | |
| ] | |
| } | |