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 +1,102 @@
+---
+pipeline_tag: image-text-to-text
+license: gemma
+base_model: google/gemma-3-27b-pt
+library_name: kerasformers
+extra_gated_heading: Access Gemma on Hugging Face
+language:
+- en
+tags:
+- keras
+- kerasformers
+- gemma3
+- gemma-3
+- image-text-to-text
+- arxiv:2503.19786
+- pytorch
+- jax
+- tf
+---
+
+*See [our collection](https://huggingface.co/kerasformers) for all Gemma 3 sizes and variants.*
+
+# Run Gemma 3 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_3-1f6feb)](https://imvision12.github.io/KerasFormers/gemma3/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Gemma_3-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/kerasformers)
+
+# kerasformers/gemma-3-27b-pt
+
+Pure-**Keras 3** conversion of [`google/gemma-3-27b-pt`](https://huggingface.co/google/gemma-3-27b-pt) for
+[kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on
+**TensorFlow / Torch / JAX**. This is a base (pretrained) checkpoint, served here as **image + text -> text** via `Gemma3ConditionalGenerate`; weights are
+stored in **bfloat16**.
+
+For model details, license, and usage terms, see Google's
+[model card](https://huggingface.co/google/gemma-3-27b-pt).
+
+## ✨ Quick start
+
+### Text-only
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from kerasformers.models.gemma3 import Gemma3TextGenerate, Gemma3Tokenizer
+
+model = Gemma3TextGenerate.from_weights("kerasformers/gemma-3-27b-pt")
+tokenizer = Gemma3Tokenizer.from_weights("kerasformers/gemma-3-27b-pt")
+
+inputs = tokenizer([{"role": "user", "content": "Hello, who are you?"}])
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(tokenizer.decode(outputs[0]))
+```
+
+### Image + text
+
+```python
+from kerasformers.models.gemma3 import Gemma3ConditionalGenerate, Gemma3Processor
+
+model = Gemma3ConditionalGenerate.from_weights("kerasformers/gemma-3-27b-pt")
+processor = Gemma3Processor.from_weights("kerasformers/gemma-3-27b-pt")
+
+conversation = [
+    {"role": "user", "content": [
+        {"type": "image", "url": "https://.../image.jpg"},
+        {"type": "text", "text": "Describe this image."},
+    ]},
+]
+inputs = processor(conversation)
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(processor.decode(outputs[0]))
+```
+
+Load any Gemma 3 variant the same way with `from_weights("kerasformers/<variant>")`:
+
+| Variant | Hub |
+| --- | --- |
+| `gemma-3-12b-it` | [kerasformers/gemma-3-12b-it](https://huggingface.co/kerasformers/gemma-3-12b-it) |
+| `gemma-3-12b-pt` | [kerasformers/gemma-3-12b-pt](https://huggingface.co/kerasformers/gemma-3-12b-pt) |
+| `gemma-3-1b-it` | [kerasformers/gemma-3-1b-it](https://huggingface.co/kerasformers/gemma-3-1b-it) |
+| `gemma-3-1b-pt` | [kerasformers/gemma-3-1b-pt](https://huggingface.co/kerasformers/gemma-3-1b-pt) |
+| `gemma-3-270m` | [kerasformers/gemma-3-270m](https://huggingface.co/kerasformers/gemma-3-270m) |
+| `gemma-3-270m-it` | [kerasformers/gemma-3-270m-it](https://huggingface.co/kerasformers/gemma-3-270m-it) |
+| `gemma-3-27b-it` | [kerasformers/gemma-3-27b-it](https://huggingface.co/kerasformers/gemma-3-27b-it) |
+| `gemma-3-27b-pt` | [kerasformers/gemma-3-27b-pt](https://huggingface.co/kerasformers/gemma-3-27b-pt) |
+| `gemma-3-4b-it` | [kerasformers/gemma-3-4b-it](https://huggingface.co/kerasformers/gemma-3-4b-it) |
+| `gemma-3-4b-pt` | [kerasformers/gemma-3-4b-pt](https://huggingface.co/kerasformers/gemma-3-4b-pt) |
+
+## 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 3 docs](https://imvision12.github.io/KerasFormers/gemma3/).
+- Community / upstream weights still work via the `hf:` prefix:
+  `Gemma3ConditionalGenerate.from_weights("hf:google/gemma-3-27b-pt")`.
+
+## Special Thanks
+
+A huge thank you to the Google Gemma authors for creating and releasing these models.
+
+License: Gemma (gated). Accept the license on the upstream Hub card before downloading.

kf_config.json

@@ -0,0 +1,39 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.1",
+  "model_module": "kerasformers.models.gemma3",
+  "model_class": "Gemma3ConditionalGenerate",
+  "variant": "gemma-3-27b-pt",
+  "weights": "model.weights.json",
+  "schema_version": 2,
+  "weight_dtype": "bfloat16",
+  "model_type": "gemma3",
+  "text_config": {
+    "vocab_size": 262208,
+    "embed_dim": 5376,
+    "mlp_dim": 21504,
+    "num_layers": 62,
+    "num_heads": 32,
+    "num_kv_heads": 16,
+    "head_dim": 128,
+    "query_pre_attn_scalar": 168.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "rope_local_theta": 10000.0,
+    "rope_scaling_factor": 8.0,
+    "tie_embeddings": true
+  },
+  "vision_config": {
+    "embed_dim": 1152,
+    "mlp_dim": 4304,
+    "num_layers": 27,
+    "num_heads": 16,
+    "image_size": 896,
+    "patch_size": 14,
+    "norm_eps": 1e-06
+  },
+  "mm_tokens_per_image": 256,
+  "image_token_id": 262144
+}

kf_preprocessor.json

@@ -0,0 +1,18 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.1",
+  "preprocessor_module": "kerasformers.models.gemma3",
+  "preprocessor_class": "Gemma3ImageProcessor",
+  "variant": "gemma-3-27b-pt",
+  "size": 896,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ]
+}

model_00000.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c958c48ebb553c356bfeef70b0f9729a1c35014b23656ccb4ab835ef6972a98
+size 5323589232

model_00001.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca689bf51e4d183534ac4ee53386f2ad63ff95e19f9f36fdba784a4c5c683fa8
+size 5324546960

model_00002.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d871c9ca5cc7e341b58708924c2bc145eb4f54bfa8265033f5e0ecd7a97c3ff
+size 5357604752

model_00003.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c499cc67fb9c4a430328cca99f340110b3d69ce6b9b87637f4aa41da1c15d0
+size 5258494864

model_00004.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76e31fe47a8468a4d8e02e36affd8afc3c10c8ce8956b4e9bc1508b1293b85e
+size 5192421776

model_00005.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab5c55f250735bafbedb34bdd4976fced6e7e6eacf31fdefa1e7c9ed6f454ff
+size 5324592016

model_00006.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219cc67402b160243f2c7219d62c9ad12404279c625d68240a876a2bb7f126a9
+size 5192421776

model_00007.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8df4ed9d7fb703715d70d78192086671f886f78e57b3a337898664411fd978
+size 5192421776

model_00008.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6649f2d5bdab94715db467a98e70cbca587fe99f98cbbea234abb72c8fe5b400
+size 5324592016

model_00009.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fa7847d2de4b07c5dbe6a44297c4720fcf67607b42ad12a6bb4d5687aef6d0
+size 5192421776

model_00010.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bd40dae200b5a9a54be317bfc0ec1408bbc79ede3f6e0b19c6382de92f0e5b
+size 2252580240

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
+size 33384570