Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,117 @@
+---
+pipeline_tag: any-to-any
+license: apache-2.0
+base_model: google/gemma-4-E4B-it
+library_name: kerasformers
+language:
+- en
+tags:
+- keras
+- kerasformers
+- gemma4
+- gemma-4
+- any-to-any
+- pytorch
+- jax
+- tf
+---
+
+*See [our collection](https://huggingface.co/kerasformers) for all Gemma 4 sizes and variants.*
+
+# Run Gemma 4 with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-181717?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-Gemma_4-1f6feb)](https://imvision12.github.io/KerasFormers/gemma4/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Gemma_4-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/kerasformers)
+
+# kerasformers/gemma-4-e4b-it
+
+Pure-**Keras 3** conversion of [`google/gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it) for
+[kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on
+**TensorFlow / Torch / JAX**. This is the **8B** variant, served here as
+**image + audio + text -> text** via `Gemma4Processor`; weights are stored in **bfloat16**.
+
+For model details, license, and usage terms, see Google's
+[model card](https://huggingface.co/google/gemma-4-E4B-it).
+
+## Gemma 4 family
+
+| Property | E2B | E4B | 12B Unified | 31B Dense |
+| --- | --- | --- | --- | --- |
+| Total Parameters | 2.3B effective (5.1B with embeddings) | 4.5B effective (8B with embeddings) | 11.95B | 30.7B |
+| Layers | 35 | 42 | 48 | 60 |
+| Sliding Window | 512 tokens | 512 tokens | 1024 tokens | 1024 tokens |
+| Context Length | 128K tokens | 128K tokens | 256K tokens | 256K tokens |
+| Vocabulary Size | 262K | 262K | 262K | 262K |
+| Supported Modalities | Text, Image, Audio | Text, Image, Audio | Text, Image, Audio | Text, Image |
+| Vision Encoder Parameters | ~150M | ~150M | - | ~550M |
+| Audio Encoder Parameters | ~300M | ~300M | - | No Audio |
+
+## ✨ Quick start
+
+### Text-only
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from kerasformers.models.gemma4 import Gemma4TextGenerate, Gemma4Tokenizer
+
+model = Gemma4TextGenerate.from_weights("kerasformers/gemma-4-e4b-it")
+tokenizer = Gemma4Tokenizer.from_weights("kerasformers/gemma-4-e4b-it")
+
+inputs = tokenizer([{"role": "user", "content": "Hello, who are you?"}])
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(tokenizer.decode(outputs[0]))
+```
+
+### Image + audio + text
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from PIL import Image
+from kerasformers.models.gemma4 import Gemma4ConditionalGenerate, Gemma4Processor
+
+model = Gemma4ConditionalGenerate.from_weights("kerasformers/gemma-4-e4b-it")
+processor = Gemma4Processor.from_weights("kerasformers/gemma-4-e4b-it")
+
+inputs = processor(conversation=[
+    {"role": "user", "content": [
+        {"type": "image", "image": Image.open("cat.jpg")},
+        {"type": "audio", "path": "clip.wav"},
+        {"type": "text", "text": "Describe the image and what you hear."},
+    ]}
+])
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(processor.decode(outputs[0]))
+```
+
+Load any Gemma 4 variant the same way with `from_weights("kerasformers/<variant>")`:
+
+| Variant | Hub |
+| --- | --- |
+| `gemma-4-12b` | [kerasformers/gemma-4-12b](https://huggingface.co/kerasformers/gemma-4-12b) |
+| `gemma-4-12b-it` | [kerasformers/gemma-4-12b-it](https://huggingface.co/kerasformers/gemma-4-12b-it) |
+| `gemma-4-26b-a4b` | [kerasformers/gemma-4-26b-a4b](https://huggingface.co/kerasformers/gemma-4-26b-a4b) |
+| `gemma-4-26b-a4b-it` | [kerasformers/gemma-4-26b-a4b-it](https://huggingface.co/kerasformers/gemma-4-26b-a4b-it) |
+| `gemma-4-31b` | [kerasformers/gemma-4-31b](https://huggingface.co/kerasformers/gemma-4-31b) |
+| `gemma-4-31b-it` | [kerasformers/gemma-4-31b-it](https://huggingface.co/kerasformers/gemma-4-31b-it) |
+| `gemma-4-e2b` | [kerasformers/gemma-4-e2b](https://huggingface.co/kerasformers/gemma-4-e2b) |
+| `gemma-4-e2b-it` | [kerasformers/gemma-4-e2b-it](https://huggingface.co/kerasformers/gemma-4-e2b-it) |
+| `gemma-4-e4b` | [kerasformers/gemma-4-e4b](https://huggingface.co/kerasformers/gemma-4-e4b) |
+| `gemma-4-e4b-it` | [kerasformers/gemma-4-e4b-it](https://huggingface.co/kerasformers/gemma-4-e4b-it) |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Loads in **bfloat16** by default. Pass `load_dtype="float32"` for full precision,
+  or `quantization="int8"` to shrink further.
+- See the [Gemma 4 docs](https://imvision12.github.io/KerasFormers/gemma4/).
+- Community / upstream weights still work via the `hf:` prefix:
+  `Gemma4ConditionalGenerate.from_weights("hf:google/gemma-4-E4B-it")`.
+
+## Special Thanks
+
+A huge thank you to the Google Gemma authors for creating and releasing these models.
+
+License: Apache 2.0.

kf_config.json

@@ -0,0 +1,122 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.1",
+  "model_module": "kerasformers.models.gemma4",
+  "model_class": "Gemma4ConditionalGenerate",
+  "variant": "gemma-4-e4b-it",
+  "weights": "model.weights.json",
+  "schema_version": 2,
+  "weight_dtype": "bfloat16",
+  "model_type": "gemma4",
+  "text_config": {
+    "vocab_size": 262144,
+    "embed_dim": 2560,
+    "mlp_dim": 10240,
+    "num_layers": 42,
+    "num_heads": 8,
+    "num_kv_heads": 2,
+    "num_global_kv_heads": 2,
+    "head_dim": 256,
+    "global_head_dim": 512,
+    "k_eq_v": false,
+    "enable_moe": false,
+    "num_experts": 0,
+    "num_experts_per_tok": 0,
+    "moe_mlp_dim": 0,
+    "sliding_window": 512,
+    "sliding_window_pattern": 6,
+    "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",
+      "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"
+    ],
+    "partial_rotary_factor": 0.25,
+    "final_logit_softcapping": 30.0,
+    "norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "rope_local_theta": 10000.0,
+    "tie_embeddings": true,
+    "hidden_size_per_layer_input": 256,
+    "vocab_size_per_layer_input": 262144,
+    "num_kv_shared_layers": 18,
+    "use_double_wide_mlp": false
+  },
+  "vision_config": {
+    "hidden_size": 768,
+    "num_layers": 16,
+    "num_heads": 12,
+    "num_kv_heads": 12,
+    "head_dim": 64,
+    "intermediate_size": 3072,
+    "patch_size": 16,
+    "position_embedding_size": 10240,
+    "pooling_kernel_size": 3,
+    "rope_theta": 100.0,
+    "eps": 1e-06,
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "audio_config": {
+    "hidden_size": 1024,
+    "num_layers": 12,
+    "num_heads": 8,
+    "conv_channels": [
+      128,
+      32
+    ],
+    "conv_kernel_size": 5,
+    "chunk_size": 12,
+    "context_left": 13,
+    "context_right": 0,
+    "logit_cap": 50.0,
+    "invalid_logits": -1000000000.0,
+    "residual_weight": 0.5,
+    "norm_eps": 1e-06,
+    "output_proj_dims": 1536,
+    "use_clipped_linears": true
+  },
+  "image_token_id": 258880,
+  "video_token_id": 258884,
+  "audio_token_id": 258881,
+  "pad_token_id": 0,
+  "use_bidirectional_vision": false
+}

kf_preprocessor.json

@@ -0,0 +1,21 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.1",
+  "preprocessor_module": "kerasformers.models.gemma4",
+  "preprocessor_class": "Gemma4ImageProcessor",
+  "variant": "gemma-4-e4b-it",
+  "patch_size": 16,
+  "max_soft_tokens": 280,
+  "pooling_kernel_size": 3,
+  "rescale_factor": 0.00392156862745098,
+  "image_mean": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "image_std": [
+    1.0,
+    1.0,
+    1.0
+  ]
+}

model_00000.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e1879a1075238479835ad5b77668cd1d039f94a5ee16effeaed0c48121ad7
+size 1971336616

model_00001.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3599eaba15ec145f57067c1d06d1a9856b7f22fff9405f6c6ca5b3834928fa2d
+size 5644517272

model_00002.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011a67e6ae475ff62a24f33604f0f9c5c6614ed78f41c19727565fda7fac09e7
+size 5371902362

model_00003.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9292d2d0e11588653b9a6b433b39d7ebb4dbbe7d866a5d0e232c67cda7e72c5
+size 2924887960

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626