EmbeddingGemma 2 Gewell bundle (text, vision, audio)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,100 @@
+---
+license: apache-2.0
+base_model:
+- google/embeddinggemma-2
+pipeline_tag: feature-extraction
+tags:
+- embeddinggemma
+- embedding
+- gewell
+- bf16
+- multimodal-embedding
+- vision
+- audio
+- video
+---
+
+# EmbeddingGemma 2 — Gewell
+
+This is the EmbeddingGemma 2 bundle used by
+[Gewell](https://github.com/LeDissolution/gewell), a single-GPU inference
+engine specialized for NVIDIA Blackwell (`sm_120`/`sm_120a`). It is a lossless
+BF16 repack of `google/embeddinggemma-2` into Gewell's native embedding layout,
+split into separately loadable text, vision and audio components. It is not a
+Transformers, Sentence Transformers, vLLM, or llama.cpp checkpoint.
+
+## Bundle contents
+
+| File | Bytes | SHA-256 |
+|---|---:|---|
+| `text.safetensors` | 542,056,504 | `84bfdbbc9d5fe6dced9fd3b572329416fe2794c9c9e3a157346bc29b7c7ff361` |
+| `vision.safetensors` | 335,543,360 | `2a146e1979e1fa9ac660aa871a2b405b92a0224b938ab4573dced85b1e43d600` |
+| `audio.safetensors` | 611,314,696 | `ca511bf78d93dfc5b9d72bd61574e36087188a357e86f6fdbe65e034ae595017` |
+| `config.json` | 4,455 | `b8f1e9931b57fbc054acdb445c41765d55b0074c58d145fa82839941ad1b5bb3` |
+| `processor_config.json` | 1,788 | `168f6a08522f3ce5dea596d94d003af2fd691742d4f41fe1f9d8cce76bfbf69c` |
+| `tokenizer.json` | 32,170,510 | `4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4` |
+
+The components hold 413 text, 211 vision/bridge and 752 audio/bridge tensors
+(1,376 total). Tensor values are copied without conversion; native startup
+validates the configuration, tokenizer, processor contract and tensor
+inventory of every loaded component.
+
+## Download and launch
+
+Follow the [Gewell build instructions](https://github.com/LeDissolution/gewell/blob/main/docs/build.md),
+then download this repository:
+
+```bash
+MODEL_DIR=/absolute/path/to/EmbeddingGemma-2-Gewell
+
+hf download LeDissolution/EmbeddingGemma-2-Gewell --local-dir "$MODEL_DIR"
+
+build/gewell serve-embeddings "$MODEL_DIR" --vision --audio
+```
+
+The server listens on `127.0.0.1:6311` and serves the OpenAI-compatible
+`POST /v1/embeddings` endpoint under the model ID `google/embeddinggemma-2`:
+
+```bash
+curl -s http://127.0.0.1:6311/v1/embeddings \
+  -H 'Content-Type: application/json' \
+  -d '{"model":"google/embeddinggemma-2","input":["task: search result | query: What causes auroras?","title: none | text: Charged particles from the sun cause auroras."],"dimensions":768}'
+```
+
+Text is always loaded. `--vision` adds image and video input; `--audio` adds
+audio input. Mixed image/video and audio requests need both. Explicit GPU
+allocations at the default 8192-token capacity, excluding CUDA/cuBLAS/cuDNN
+overhead:
+
+| Options | Weight bytes | Scratch bytes |
+|---|---:|---:|
+| text only | 274,210,816 | 167,773,696 |
+| `--vision` | 610,017,280 | 178,782,528 |
+| `--vision --audio` | 1,223,507,968 | 1,028,441,648 |
+
+The token-embedding table stays in host memory. Inputs support up to 8192
+tokens including BOS/EOS and 128/256/512/768 output dimensions. Task prefixes
+are not inserted automatically; supply them as described in the upstream
+model card.
+
+The engine was developed and tested on an RTX PRO 6000 Blackwell. See the
+[model guide](https://github.com/LeDissolution/gewell/blob/main/docs/models.md),
+[CLI reference](https://github.com/LeDissolution/gewell/blob/main/docs/cli.md)
+and [HTTP API documentation](https://github.com/LeDissolution/gewell/blob/main/docs/http-api.md)
+for request formats, media limits and serving options.
+
+## Scope and provenance
+
+This repository was created with
+
+```bash
+python3 tools/extract_embeddinggemma2.py --snapshot SNAPSHOT --vision --audio --output MODEL_DIR
+```
+
+from `google/embeddinggemma-2` at revision
+`914f7f89142e33e77833254d9c9b90c3cef7303b`. Extraction is deterministic; you
+can reproduce these files from the upstream snapshot instead of downloading
+them.
+
+Use is subject to the upstream
+[EmbeddingGemma 2 license and terms](https://huggingface.co/google/embeddinggemma-2).

audio.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca511bf78d93dfc5b9d72bd61574e36087188a357e86f6fdbe65e034ae595017
+size 611314696

config.json

@@ -0,0 +1,177 @@
+{
+  "architectures": [
+    "EmbeddingGemma2Model"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "embedding_gemma2",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "embedding_dim": 768,
+    "eos_token_id": 1,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 512,
+    "hidden_size_per_layer_input": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "embedding_gemma2_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "per_layer_config": {
+      "05": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "11": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "17": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      },
+      "23": {
+        "head_dim": 512,
+        "num_key_value_heads": 1
+      }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "vocab_size": 262144
+  },
+  "transformers_version": "5.18.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "axial"
+    },
+    "standardize": false,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280
+}

processor_config.json

@@ -0,0 +1,78 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 280,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "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
+  },
+  "image_seq_length": 280,
+  "processor_class": "EmbeddingGemma2Processor",
+  "video_processor": {
+    "add_timestamps": false,
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 1,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_frames": 32,
+    "max_soft_tokens": 140,
+    "overflow_strategy": "uniform",
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "EmbeddingGemma2VideoProcessor"
+  }
+}

text.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84bfdbbc9d5fe6dced9fd3b572329416fe2794c9c9e3a157346bc29b7c7ff361
+size 542056504

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4
+size 32170510

vision.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a146e1979e1fa9ac660aa871a2b405b92a0224b938ab4573dced85b1e43d600
+size 335543360