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 +1,65 @@
+---
+pipeline_tag: image-text-to-text
+license: apache-2.0
+base_model: OpenGVLab/InternVL3_5-2B-HF
+library_name: kerasformers
+language:
+- en
+tags:
+- keras
+- kerasformers
+- internvl
+- internvl3-5
+- multimodal
+- vision
+- image-text-to-text
+- pytorch
+- jax
+- tf
+---
+
+# Run InternVL3.5 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-InternVL-1f6feb)](https://imvision12.github.io/KerasFormers/internvl/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-InternVL-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/collections/kerasformers/internvl-6a8277076dbb163f53241dbd)
+
+# kerasformers/internvl3.5-2b
+
+Pure-**Keras 3** conversion of [`OpenGVLab/InternVL3_5-2B-HF`](https://huggingface.co/OpenGVLab/InternVL3_5-2B-HF) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**. This is a **InternVL3.5** checkpoint, served as **image + text -> text** via `InternVLProcessor`; weights are stored in **bfloat16**.
+
+For model details, license, and usage terms, see the upstream [model card](https://huggingface.co/OpenGVLab/InternVL3_5-2B-HF).
+
+Paper: [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency (arXiv:2508.18265)](https://arxiv.org/abs/2508.18265) · [HF Papers](https://huggingface.co/papers/2508.18265)
+
+Paper: [Qwen3 Technical Report (arXiv:2505.09388)](https://arxiv.org/abs/2505.09388) · [HF Papers](https://huggingface.co/papers/2505.09388)
+
+Paper: [YaRN: Efficient Context Window Extension of Large Language Models (arXiv:2309.00071)](https://arxiv.org/abs/2309.00071) · [HF Papers](https://huggingface.co/papers/2309.00071)
+
+## ✨ Quick start
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from PIL import Image
+from kerasformers.models.internvl import InternVLConditionalGenerate, InternVLProcessor
+
+model = InternVLConditionalGenerate.from_weights("kerasformers/internvl3.5-2b")
+processor = InternVLProcessor.from_weights("kerasformers/internvl3.5-2b")
+
+inputs = processor(conversation=[
+    {"role": "user", "content": [
+        {"type": "image", "image": Image.open("photo.jpg")},
+        {"type": "text", "text": "Describe this image in one sentence."},
+    ]}
+])
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(processor.decode(outputs[0]))
+```
+
+Load any InternVL variant the same way with `from_weights("kerasformers/<variant>")`. Browse them all in the [InternVL collection](https://huggingface.co/collections/kerasformers/internvl-6a8277076dbb163f53241dbd).
+
+## Special Thanks
+
+A huge thank you to the OpenGVLab team for creating and releasing the InternVL models.
+
+License: `apache-2.0` (per the upstream model card).

kf_config.json

@@ -0,0 +1,45 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.4",
+  "model_module": "kerasformers.models.internvl",
+  "model_class": "InternVLConditionalGenerate",
+  "variant": "internvl3.5-2b",
+  "weights": "model.weights.json",
+  "schema_version": 2,
+  "weight_dtype": "bfloat16",
+  "model_type": "internvl",
+  "text_config": {
+    "vocab_size": 151936,
+    "embed_dim": 2048,
+    "mlp_dim": 6144,
+    "num_layers": 28,
+    "num_heads": 16,
+    "num_kv_heads": 8,
+    "head_dim": 128,
+    "text_backbone": "qwen3",
+    "norm_eps": 1e-06,
+    "rope_theta": 1000000,
+    "tie_embeddings": false,
+    "num_experts": 0,
+    "num_experts_per_tok": 0,
+    "moe_mlp_dim": 0,
+    "norm_topk_prob": true,
+    "decoder_sparse_step": 1,
+    "mlp_only_layers": []
+  },
+  "vision_config": {
+    "embed_dim": 1024,
+    "mlp_dim": 4096,
+    "num_layers": 24,
+    "num_heads": 16,
+    "image_size": 448,
+    "patch_size": 14,
+    "attention_bias": true,
+    "qk_norm": false,
+    "norm_type": "layer_norm",
+    "norm_eps": 1e-06,
+    "layer_scale_init": 0.1
+  },
+  "downsample_ratio": 0.5,
+  "image_token_id": 151671
+}

kf_preprocessor.json

@@ -0,0 +1,22 @@
+{
+  "library_name": "kerasformers",
+  "kerasformers_version": "1.2.4",
+  "preprocessor_module": "kerasformers.models.internvl",
+  "preprocessor_class": "InternVLImageProcessor",
+  "variant": "internvl3.5-2b",
+  "size": 448,
+  "min_patches": 1,
+  "max_patches": 12,
+  "crop_to_patches": true,
+  "use_thumbnail": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ]
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c87a9ab01326bfd65ad0f0d878ca39f9e94b44c043387f746cecab5f23976d
+size 4698359888

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9d18660f656ae5a87df2d5d6ed990e80f292d3473c1a35cae8259a5d28cd67
+size 11424484