Commit ·
8a3776f
0
Parent(s):
Super-squash branch 'main' using huggingface_hub
Browse files- .gitattributes +36 -0
- README.md +65 -0
- kf_config.json +45 -0
- kf_preprocessor.json +22 -0
- model.weights.json +1069 -0
- model_00000.weights.h5 +3 -0
- model_00001.weights.h5 +3 -0
- tokenizer.json +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-text-to-text
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: OpenGVLab/InternVL3_5-4B-HF
|
| 5 |
+
library_name: kerasformers
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- keras
|
| 10 |
+
- kerasformers
|
| 11 |
+
- internvl
|
| 12 |
+
- internvl3-5
|
| 13 |
+
- multimodal
|
| 14 |
+
- vision
|
| 15 |
+
- image-text-to-text
|
| 16 |
+
- pytorch
|
| 17 |
+
- jax
|
| 18 |
+
- tf
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# Run InternVL3.5 with Keras 3: JAX, PyTorch, or TensorFlow
|
| 22 |
+
|
| 23 |
+
[](https://github.com/IMvision12/KerasFormers) [](https://imvision12.github.io/KerasFormers/internvl/) [](https://huggingface.co/collections/kerasformers/internvl-6a8277076dbb163f53241dbd)
|
| 24 |
+
|
| 25 |
+
# kerasformers/internvl3.5-4b
|
| 26 |
+
|
| 27 |
+
Pure-**Keras 3** conversion of [`OpenGVLab/InternVL3_5-4B-HF`](https://huggingface.co/OpenGVLab/InternVL3_5-4B-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**.
|
| 28 |
+
|
| 29 |
+
For model details, license, and usage terms, see the upstream [model card](https://huggingface.co/OpenGVLab/InternVL3_5-4B-HF).
|
| 30 |
+
|
| 31 |
+
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)
|
| 32 |
+
|
| 33 |
+
Paper: [Qwen3 Technical Report (arXiv:2505.09388)](https://arxiv.org/abs/2505.09388) · [HF Papers](https://huggingface.co/papers/2505.09388)
|
| 34 |
+
|
| 35 |
+
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)
|
| 36 |
+
|
| 37 |
+
## ✨ Quick start
|
| 38 |
+
|
| 39 |
+
```python
|
| 40 |
+
import os
|
| 41 |
+
os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow"
|
| 42 |
+
|
| 43 |
+
from PIL import Image
|
| 44 |
+
from kerasformers.models.internvl import InternVLConditionalGenerate, InternVLProcessor
|
| 45 |
+
|
| 46 |
+
model = InternVLConditionalGenerate.from_weights("kerasformers/internvl3.5-4b")
|
| 47 |
+
processor = InternVLProcessor.from_weights("kerasformers/internvl3.5-4b")
|
| 48 |
+
|
| 49 |
+
inputs = processor(conversation=[
|
| 50 |
+
{"role": "user", "content": [
|
| 51 |
+
{"type": "image", "image": Image.open("photo.jpg")},
|
| 52 |
+
{"type": "text", "text": "Describe this image in one sentence."},
|
| 53 |
+
]}
|
| 54 |
+
])
|
| 55 |
+
outputs = model.generate(**inputs, max_new_tokens=64)
|
| 56 |
+
print(processor.decode(outputs[0]))
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
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).
|
| 60 |
+
|
| 61 |
+
## Special Thanks
|
| 62 |
+
|
| 63 |
+
A huge thank you to the OpenGVLab team for creating and releasing the InternVL models.
|
| 64 |
+
|
| 65 |
+
License: `apache-2.0` (per the upstream model card).
|
kf_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.2.4",
|
| 4 |
+
"model_module": "kerasformers.models.internvl",
|
| 5 |
+
"model_class": "InternVLConditionalGenerate",
|
| 6 |
+
"variant": "internvl3.5-4b",
|
| 7 |
+
"weights": "model.weights.json",
|
| 8 |
+
"schema_version": 2,
|
| 9 |
+
"weight_dtype": "bfloat16",
|
| 10 |
+
"model_type": "internvl",
|
| 11 |
+
"text_config": {
|
| 12 |
+
"vocab_size": 151936,
|
| 13 |
+
"embed_dim": 2560,
|
| 14 |
+
"mlp_dim": 9728,
|
| 15 |
+
"num_layers": 36,
|
| 16 |
+
"num_heads": 32,
|
| 17 |
+
"num_kv_heads": 8,
|
| 18 |
+
"head_dim": 128,
|
| 19 |
+
"text_backbone": "qwen3",
|
| 20 |
+
"norm_eps": 1e-06,
|
| 21 |
+
"rope_theta": 1000000,
|
| 22 |
+
"tie_embeddings": false,
|
| 23 |
+
"num_experts": 0,
|
| 24 |
+
"num_experts_per_tok": 0,
|
| 25 |
+
"moe_mlp_dim": 0,
|
| 26 |
+
"norm_topk_prob": true,
|
| 27 |
+
"decoder_sparse_step": 1,
|
| 28 |
+
"mlp_only_layers": []
|
| 29 |
+
},
|
| 30 |
+
"vision_config": {
|
| 31 |
+
"embed_dim": 1024,
|
| 32 |
+
"mlp_dim": 4096,
|
| 33 |
+
"num_layers": 24,
|
| 34 |
+
"num_heads": 16,
|
| 35 |
+
"image_size": 448,
|
| 36 |
+
"patch_size": 14,
|
| 37 |
+
"attention_bias": true,
|
| 38 |
+
"qk_norm": false,
|
| 39 |
+
"norm_type": "layer_norm",
|
| 40 |
+
"norm_eps": 1e-06,
|
| 41 |
+
"layer_scale_init": 0.1
|
| 42 |
+
},
|
| 43 |
+
"downsample_ratio": 0.5,
|
| 44 |
+
"image_token_id": 151671
|
| 45 |
+
}
|
kf_preprocessor.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.2.4",
|
| 4 |
+
"preprocessor_module": "kerasformers.models.internvl",
|
| 5 |
+
"preprocessor_class": "InternVLImageProcessor",
|
| 6 |
+
"variant": "internvl3.5-4b",
|
| 7 |
+
"size": 448,
|
| 8 |
+
"min_patches": 1,
|
| 9 |
+
"max_patches": 12,
|
| 10 |
+
"crop_to_patches": true,
|
| 11 |
+
"use_thumbnail": true,
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.485,
|
| 14 |
+
0.456,
|
| 15 |
+
0.406
|
| 16 |
+
],
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.229,
|
| 19 |
+
0.224,
|
| 20 |
+
0.225
|
| 21 |
+
]
|
| 22 |
+
}
|
model.weights.json
ADDED
|
@@ -0,0 +1,1069 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 9464978432.0
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/vars": [
|
| 7 |
+
"model_00000.weights.h5"
|
| 8 |
+
],
|
| 9 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/attention/key/vars": [
|
| 10 |
+
"model_00000.weights.h5"
|
| 11 |
+
],
|
| 12 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/attention/output_proj/vars": [
|
| 13 |
+
"model_00000.weights.h5"
|
| 14 |
+
],
|
| 15 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/attention/query/vars": [
|
| 16 |
+
"model_00000.weights.h5"
|
| 17 |
+
],
|
| 18 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/attention/value/vars": [
|
| 19 |
+
"model_00000.weights.h5"
|
| 20 |
+
],
|
| 21 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/layernorm_after/vars": [
|
| 22 |
+
"model_00000.weights.h5"
|
| 23 |
+
],
|
| 24 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/layernorm_before/vars": [
|
| 25 |
+
"model_00000.weights.h5"
|
| 26 |
+
],
|
| 27 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/mlp/fc1/vars": [
|
| 28 |
+
"model_00000.weights.h5"
|
| 29 |
+
],
|
| 30 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer/mlp/fc2/vars": [
|
| 31 |
+
"model_00000.weights.h5"
|
| 32 |
+
],
|
| 33 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/vars": [
|
| 34 |
+
"model_00000.weights.h5"
|
| 35 |
+
],
|
| 36 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/attention/key/vars": [
|
| 37 |
+
"model_00000.weights.h5"
|
| 38 |
+
],
|
| 39 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/attention/output_proj/vars": [
|
| 40 |
+
"model_00000.weights.h5"
|
| 41 |
+
],
|
| 42 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/attention/query/vars": [
|
| 43 |
+
"model_00000.weights.h5"
|
| 44 |
+
],
|
| 45 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/attention/value/vars": [
|
| 46 |
+
"model_00000.weights.h5"
|
| 47 |
+
],
|
| 48 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/layernorm_after/vars": [
|
| 49 |
+
"model_00000.weights.h5"
|
| 50 |
+
],
|
| 51 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/layernorm_before/vars": [
|
| 52 |
+
"model_00000.weights.h5"
|
| 53 |
+
],
|
| 54 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/mlp/fc1/vars": [
|
| 55 |
+
"model_00000.weights.h5"
|
| 56 |
+
],
|
| 57 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_1/mlp/fc2/vars": [
|
| 58 |
+
"model_00000.weights.h5"
|
| 59 |
+
],
|
| 60 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/vars": [
|
| 61 |
+
"model_00000.weights.h5"
|
| 62 |
+
],
|
| 63 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/attention/key/vars": [
|
| 64 |
+
"model_00000.weights.h5"
|
| 65 |
+
],
|
| 66 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/attention/output_proj/vars": [
|
| 67 |
+
"model_00000.weights.h5"
|
| 68 |
+
],
|
| 69 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/attention/query/vars": [
|
| 70 |
+
"model_00000.weights.h5"
|
| 71 |
+
],
|
| 72 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/attention/value/vars": [
|
| 73 |
+
"model_00000.weights.h5"
|
| 74 |
+
],
|
| 75 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/layernorm_after/vars": [
|
| 76 |
+
"model_00000.weights.h5"
|
| 77 |
+
],
|
| 78 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/layernorm_before/vars": [
|
| 79 |
+
"model_00000.weights.h5"
|
| 80 |
+
],
|
| 81 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/mlp/fc1/vars": [
|
| 82 |
+
"model_00000.weights.h5"
|
| 83 |
+
],
|
| 84 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_2/mlp/fc2/vars": [
|
| 85 |
+
"model_00000.weights.h5"
|
| 86 |
+
],
|
| 87 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/vars": [
|
| 88 |
+
"model_00000.weights.h5"
|
| 89 |
+
],
|
| 90 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/attention/key/vars": [
|
| 91 |
+
"model_00000.weights.h5"
|
| 92 |
+
],
|
| 93 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/attention/output_proj/vars": [
|
| 94 |
+
"model_00000.weights.h5"
|
| 95 |
+
],
|
| 96 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/attention/query/vars": [
|
| 97 |
+
"model_00000.weights.h5"
|
| 98 |
+
],
|
| 99 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/attention/value/vars": [
|
| 100 |
+
"model_00000.weights.h5"
|
| 101 |
+
],
|
| 102 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/layernorm_after/vars": [
|
| 103 |
+
"model_00000.weights.h5"
|
| 104 |
+
],
|
| 105 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/layernorm_before/vars": [
|
| 106 |
+
"model_00000.weights.h5"
|
| 107 |
+
],
|
| 108 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/mlp/fc1/vars": [
|
| 109 |
+
"model_00000.weights.h5"
|
| 110 |
+
],
|
| 111 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_3/mlp/fc2/vars": [
|
| 112 |
+
"model_00000.weights.h5"
|
| 113 |
+
],
|
| 114 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/vars": [
|
| 115 |
+
"model_00000.weights.h5"
|
| 116 |
+
],
|
| 117 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/attention/key/vars": [
|
| 118 |
+
"model_00000.weights.h5"
|
| 119 |
+
],
|
| 120 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/attention/output_proj/vars": [
|
| 121 |
+
"model_00000.weights.h5"
|
| 122 |
+
],
|
| 123 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/attention/query/vars": [
|
| 124 |
+
"model_00000.weights.h5"
|
| 125 |
+
],
|
| 126 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/attention/value/vars": [
|
| 127 |
+
"model_00000.weights.h5"
|
| 128 |
+
],
|
| 129 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/layernorm_after/vars": [
|
| 130 |
+
"model_00000.weights.h5"
|
| 131 |
+
],
|
| 132 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/layernorm_before/vars": [
|
| 133 |
+
"model_00000.weights.h5"
|
| 134 |
+
],
|
| 135 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/mlp/fc1/vars": [
|
| 136 |
+
"model_00000.weights.h5"
|
| 137 |
+
],
|
| 138 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_4/mlp/fc2/vars": [
|
| 139 |
+
"model_00000.weights.h5"
|
| 140 |
+
],
|
| 141 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/vars": [
|
| 142 |
+
"model_00000.weights.h5"
|
| 143 |
+
],
|
| 144 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/attention/key/vars": [
|
| 145 |
+
"model_00000.weights.h5"
|
| 146 |
+
],
|
| 147 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/attention/output_proj/vars": [
|
| 148 |
+
"model_00000.weights.h5"
|
| 149 |
+
],
|
| 150 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/attention/query/vars": [
|
| 151 |
+
"model_00000.weights.h5"
|
| 152 |
+
],
|
| 153 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/attention/value/vars": [
|
| 154 |
+
"model_00000.weights.h5"
|
| 155 |
+
],
|
| 156 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/layernorm_after/vars": [
|
| 157 |
+
"model_00000.weights.h5"
|
| 158 |
+
],
|
| 159 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/layernorm_before/vars": [
|
| 160 |
+
"model_00000.weights.h5"
|
| 161 |
+
],
|
| 162 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/mlp/fc1/vars": [
|
| 163 |
+
"model_00000.weights.h5"
|
| 164 |
+
],
|
| 165 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_5/mlp/fc2/vars": [
|
| 166 |
+
"model_00000.weights.h5"
|
| 167 |
+
],
|
| 168 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/vars": [
|
| 169 |
+
"model_00000.weights.h5"
|
| 170 |
+
],
|
| 171 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/attention/key/vars": [
|
| 172 |
+
"model_00000.weights.h5"
|
| 173 |
+
],
|
| 174 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/attention/output_proj/vars": [
|
| 175 |
+
"model_00000.weights.h5"
|
| 176 |
+
],
|
| 177 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/attention/query/vars": [
|
| 178 |
+
"model_00000.weights.h5"
|
| 179 |
+
],
|
| 180 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/attention/value/vars": [
|
| 181 |
+
"model_00000.weights.h5"
|
| 182 |
+
],
|
| 183 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/layernorm_after/vars": [
|
| 184 |
+
"model_00000.weights.h5"
|
| 185 |
+
],
|
| 186 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/layernorm_before/vars": [
|
| 187 |
+
"model_00000.weights.h5"
|
| 188 |
+
],
|
| 189 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/mlp/fc1/vars": [
|
| 190 |
+
"model_00000.weights.h5"
|
| 191 |
+
],
|
| 192 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_6/mlp/fc2/vars": [
|
| 193 |
+
"model_00000.weights.h5"
|
| 194 |
+
],
|
| 195 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/vars": [
|
| 196 |
+
"model_00000.weights.h5"
|
| 197 |
+
],
|
| 198 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/attention/key/vars": [
|
| 199 |
+
"model_00000.weights.h5"
|
| 200 |
+
],
|
| 201 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/attention/output_proj/vars": [
|
| 202 |
+
"model_00000.weights.h5"
|
| 203 |
+
],
|
| 204 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/attention/query/vars": [
|
| 205 |
+
"model_00000.weights.h5"
|
| 206 |
+
],
|
| 207 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/attention/value/vars": [
|
| 208 |
+
"model_00000.weights.h5"
|
| 209 |
+
],
|
| 210 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/layernorm_after/vars": [
|
| 211 |
+
"model_00000.weights.h5"
|
| 212 |
+
],
|
| 213 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/layernorm_before/vars": [
|
| 214 |
+
"model_00000.weights.h5"
|
| 215 |
+
],
|
| 216 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/mlp/fc1/vars": [
|
| 217 |
+
"model_00000.weights.h5"
|
| 218 |
+
],
|
| 219 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_7/mlp/fc2/vars": [
|
| 220 |
+
"model_00000.weights.h5"
|
| 221 |
+
],
|
| 222 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/vars": [
|
| 223 |
+
"model_00000.weights.h5"
|
| 224 |
+
],
|
| 225 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/attention/key/vars": [
|
| 226 |
+
"model_00000.weights.h5"
|
| 227 |
+
],
|
| 228 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/attention/output_proj/vars": [
|
| 229 |
+
"model_00000.weights.h5"
|
| 230 |
+
],
|
| 231 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/attention/query/vars": [
|
| 232 |
+
"model_00000.weights.h5"
|
| 233 |
+
],
|
| 234 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/attention/value/vars": [
|
| 235 |
+
"model_00000.weights.h5"
|
| 236 |
+
],
|
| 237 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/layernorm_after/vars": [
|
| 238 |
+
"model_00000.weights.h5"
|
| 239 |
+
],
|
| 240 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/layernorm_before/vars": [
|
| 241 |
+
"model_00000.weights.h5"
|
| 242 |
+
],
|
| 243 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/mlp/fc1/vars": [
|
| 244 |
+
"model_00000.weights.h5"
|
| 245 |
+
],
|
| 246 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_8/mlp/fc2/vars": [
|
| 247 |
+
"model_00000.weights.h5"
|
| 248 |
+
],
|
| 249 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/vars": [
|
| 250 |
+
"model_00000.weights.h5"
|
| 251 |
+
],
|
| 252 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/attention/key/vars": [
|
| 253 |
+
"model_00000.weights.h5"
|
| 254 |
+
],
|
| 255 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/attention/output_proj/vars": [
|
| 256 |
+
"model_00000.weights.h5"
|
| 257 |
+
],
|
| 258 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/attention/query/vars": [
|
| 259 |
+
"model_00000.weights.h5"
|
| 260 |
+
],
|
| 261 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/attention/value/vars": [
|
| 262 |
+
"model_00000.weights.h5"
|
| 263 |
+
],
|
| 264 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/layernorm_after/vars": [
|
| 265 |
+
"model_00000.weights.h5"
|
| 266 |
+
],
|
| 267 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/layernorm_before/vars": [
|
| 268 |
+
"model_00000.weights.h5"
|
| 269 |
+
],
|
| 270 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/mlp/fc1/vars": [
|
| 271 |
+
"model_00000.weights.h5"
|
| 272 |
+
],
|
| 273 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_9/mlp/fc2/vars": [
|
| 274 |
+
"model_00000.weights.h5"
|
| 275 |
+
],
|
| 276 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/vars": [
|
| 277 |
+
"model_00000.weights.h5"
|
| 278 |
+
],
|
| 279 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/attention/key/vars": [
|
| 280 |
+
"model_00000.weights.h5"
|
| 281 |
+
],
|
| 282 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/attention/output_proj/vars": [
|
| 283 |
+
"model_00000.weights.h5"
|
| 284 |
+
],
|
| 285 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/attention/query/vars": [
|
| 286 |
+
"model_00000.weights.h5"
|
| 287 |
+
],
|
| 288 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/attention/value/vars": [
|
| 289 |
+
"model_00000.weights.h5"
|
| 290 |
+
],
|
| 291 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/layernorm_after/vars": [
|
| 292 |
+
"model_00000.weights.h5"
|
| 293 |
+
],
|
| 294 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/layernorm_before/vars": [
|
| 295 |
+
"model_00000.weights.h5"
|
| 296 |
+
],
|
| 297 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/mlp/fc1/vars": [
|
| 298 |
+
"model_00000.weights.h5"
|
| 299 |
+
],
|
| 300 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_10/mlp/fc2/vars": [
|
| 301 |
+
"model_00000.weights.h5"
|
| 302 |
+
],
|
| 303 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/vars": [
|
| 304 |
+
"model_00000.weights.h5"
|
| 305 |
+
],
|
| 306 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/attention/key/vars": [
|
| 307 |
+
"model_00000.weights.h5"
|
| 308 |
+
],
|
| 309 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/attention/output_proj/vars": [
|
| 310 |
+
"model_00000.weights.h5"
|
| 311 |
+
],
|
| 312 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/attention/query/vars": [
|
| 313 |
+
"model_00000.weights.h5"
|
| 314 |
+
],
|
| 315 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/attention/value/vars": [
|
| 316 |
+
"model_00000.weights.h5"
|
| 317 |
+
],
|
| 318 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/layernorm_after/vars": [
|
| 319 |
+
"model_00000.weights.h5"
|
| 320 |
+
],
|
| 321 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/layernorm_before/vars": [
|
| 322 |
+
"model_00000.weights.h5"
|
| 323 |
+
],
|
| 324 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/mlp/fc1/vars": [
|
| 325 |
+
"model_00000.weights.h5"
|
| 326 |
+
],
|
| 327 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_11/mlp/fc2/vars": [
|
| 328 |
+
"model_00000.weights.h5"
|
| 329 |
+
],
|
| 330 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/vars": [
|
| 331 |
+
"model_00000.weights.h5"
|
| 332 |
+
],
|
| 333 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/attention/key/vars": [
|
| 334 |
+
"model_00000.weights.h5"
|
| 335 |
+
],
|
| 336 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/attention/output_proj/vars": [
|
| 337 |
+
"model_00000.weights.h5"
|
| 338 |
+
],
|
| 339 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/attention/query/vars": [
|
| 340 |
+
"model_00000.weights.h5"
|
| 341 |
+
],
|
| 342 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/attention/value/vars": [
|
| 343 |
+
"model_00000.weights.h5"
|
| 344 |
+
],
|
| 345 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/layernorm_after/vars": [
|
| 346 |
+
"model_00000.weights.h5"
|
| 347 |
+
],
|
| 348 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/layernorm_before/vars": [
|
| 349 |
+
"model_00000.weights.h5"
|
| 350 |
+
],
|
| 351 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/mlp/fc1/vars": [
|
| 352 |
+
"model_00000.weights.h5"
|
| 353 |
+
],
|
| 354 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_12/mlp/fc2/vars": [
|
| 355 |
+
"model_00000.weights.h5"
|
| 356 |
+
],
|
| 357 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/vars": [
|
| 358 |
+
"model_00000.weights.h5"
|
| 359 |
+
],
|
| 360 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/attention/key/vars": [
|
| 361 |
+
"model_00000.weights.h5"
|
| 362 |
+
],
|
| 363 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/attention/output_proj/vars": [
|
| 364 |
+
"model_00000.weights.h5"
|
| 365 |
+
],
|
| 366 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/attention/query/vars": [
|
| 367 |
+
"model_00000.weights.h5"
|
| 368 |
+
],
|
| 369 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/attention/value/vars": [
|
| 370 |
+
"model_00000.weights.h5"
|
| 371 |
+
],
|
| 372 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/layernorm_after/vars": [
|
| 373 |
+
"model_00000.weights.h5"
|
| 374 |
+
],
|
| 375 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/layernorm_before/vars": [
|
| 376 |
+
"model_00000.weights.h5"
|
| 377 |
+
],
|
| 378 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/mlp/fc1/vars": [
|
| 379 |
+
"model_00000.weights.h5"
|
| 380 |
+
],
|
| 381 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_13/mlp/fc2/vars": [
|
| 382 |
+
"model_00000.weights.h5"
|
| 383 |
+
],
|
| 384 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/vars": [
|
| 385 |
+
"model_00000.weights.h5"
|
| 386 |
+
],
|
| 387 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/attention/key/vars": [
|
| 388 |
+
"model_00000.weights.h5"
|
| 389 |
+
],
|
| 390 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/attention/output_proj/vars": [
|
| 391 |
+
"model_00000.weights.h5"
|
| 392 |
+
],
|
| 393 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/attention/query/vars": [
|
| 394 |
+
"model_00000.weights.h5"
|
| 395 |
+
],
|
| 396 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/attention/value/vars": [
|
| 397 |
+
"model_00000.weights.h5"
|
| 398 |
+
],
|
| 399 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/layernorm_after/vars": [
|
| 400 |
+
"model_00000.weights.h5"
|
| 401 |
+
],
|
| 402 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/layernorm_before/vars": [
|
| 403 |
+
"model_00000.weights.h5"
|
| 404 |
+
],
|
| 405 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/mlp/fc1/vars": [
|
| 406 |
+
"model_00000.weights.h5"
|
| 407 |
+
],
|
| 408 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_14/mlp/fc2/vars": [
|
| 409 |
+
"model_00000.weights.h5"
|
| 410 |
+
],
|
| 411 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/vars": [
|
| 412 |
+
"model_00000.weights.h5"
|
| 413 |
+
],
|
| 414 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/attention/key/vars": [
|
| 415 |
+
"model_00000.weights.h5"
|
| 416 |
+
],
|
| 417 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/attention/output_proj/vars": [
|
| 418 |
+
"model_00000.weights.h5"
|
| 419 |
+
],
|
| 420 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/attention/query/vars": [
|
| 421 |
+
"model_00000.weights.h5"
|
| 422 |
+
],
|
| 423 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/attention/value/vars": [
|
| 424 |
+
"model_00000.weights.h5"
|
| 425 |
+
],
|
| 426 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/layernorm_after/vars": [
|
| 427 |
+
"model_00000.weights.h5"
|
| 428 |
+
],
|
| 429 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/layernorm_before/vars": [
|
| 430 |
+
"model_00000.weights.h5"
|
| 431 |
+
],
|
| 432 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/mlp/fc1/vars": [
|
| 433 |
+
"model_00000.weights.h5"
|
| 434 |
+
],
|
| 435 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_15/mlp/fc2/vars": [
|
| 436 |
+
"model_00000.weights.h5"
|
| 437 |
+
],
|
| 438 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/vars": [
|
| 439 |
+
"model_00000.weights.h5"
|
| 440 |
+
],
|
| 441 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/attention/key/vars": [
|
| 442 |
+
"model_00000.weights.h5"
|
| 443 |
+
],
|
| 444 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/attention/output_proj/vars": [
|
| 445 |
+
"model_00000.weights.h5"
|
| 446 |
+
],
|
| 447 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/attention/query/vars": [
|
| 448 |
+
"model_00000.weights.h5"
|
| 449 |
+
],
|
| 450 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/attention/value/vars": [
|
| 451 |
+
"model_00000.weights.h5"
|
| 452 |
+
],
|
| 453 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/layernorm_after/vars": [
|
| 454 |
+
"model_00000.weights.h5"
|
| 455 |
+
],
|
| 456 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/layernorm_before/vars": [
|
| 457 |
+
"model_00000.weights.h5"
|
| 458 |
+
],
|
| 459 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/mlp/fc1/vars": [
|
| 460 |
+
"model_00000.weights.h5"
|
| 461 |
+
],
|
| 462 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_16/mlp/fc2/vars": [
|
| 463 |
+
"model_00000.weights.h5"
|
| 464 |
+
],
|
| 465 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/vars": [
|
| 466 |
+
"model_00000.weights.h5"
|
| 467 |
+
],
|
| 468 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/attention/key/vars": [
|
| 469 |
+
"model_00000.weights.h5"
|
| 470 |
+
],
|
| 471 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/attention/output_proj/vars": [
|
| 472 |
+
"model_00000.weights.h5"
|
| 473 |
+
],
|
| 474 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/attention/query/vars": [
|
| 475 |
+
"model_00000.weights.h5"
|
| 476 |
+
],
|
| 477 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/attention/value/vars": [
|
| 478 |
+
"model_00000.weights.h5"
|
| 479 |
+
],
|
| 480 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/layernorm_after/vars": [
|
| 481 |
+
"model_00000.weights.h5"
|
| 482 |
+
],
|
| 483 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/layernorm_before/vars": [
|
| 484 |
+
"model_00000.weights.h5"
|
| 485 |
+
],
|
| 486 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/mlp/fc1/vars": [
|
| 487 |
+
"model_00000.weights.h5"
|
| 488 |
+
],
|
| 489 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_17/mlp/fc2/vars": [
|
| 490 |
+
"model_00000.weights.h5"
|
| 491 |
+
],
|
| 492 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/vars": [
|
| 493 |
+
"model_00000.weights.h5"
|
| 494 |
+
],
|
| 495 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/attention/key/vars": [
|
| 496 |
+
"model_00000.weights.h5"
|
| 497 |
+
],
|
| 498 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/attention/output_proj/vars": [
|
| 499 |
+
"model_00000.weights.h5"
|
| 500 |
+
],
|
| 501 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/attention/query/vars": [
|
| 502 |
+
"model_00000.weights.h5"
|
| 503 |
+
],
|
| 504 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/attention/value/vars": [
|
| 505 |
+
"model_00000.weights.h5"
|
| 506 |
+
],
|
| 507 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/layernorm_after/vars": [
|
| 508 |
+
"model_00000.weights.h5"
|
| 509 |
+
],
|
| 510 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/layernorm_before/vars": [
|
| 511 |
+
"model_00000.weights.h5"
|
| 512 |
+
],
|
| 513 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/mlp/fc1/vars": [
|
| 514 |
+
"model_00000.weights.h5"
|
| 515 |
+
],
|
| 516 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_18/mlp/fc2/vars": [
|
| 517 |
+
"model_00000.weights.h5"
|
| 518 |
+
],
|
| 519 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/vars": [
|
| 520 |
+
"model_00000.weights.h5"
|
| 521 |
+
],
|
| 522 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/attention/key/vars": [
|
| 523 |
+
"model_00000.weights.h5"
|
| 524 |
+
],
|
| 525 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/attention/output_proj/vars": [
|
| 526 |
+
"model_00000.weights.h5"
|
| 527 |
+
],
|
| 528 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/attention/query/vars": [
|
| 529 |
+
"model_00000.weights.h5"
|
| 530 |
+
],
|
| 531 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/attention/value/vars": [
|
| 532 |
+
"model_00000.weights.h5"
|
| 533 |
+
],
|
| 534 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/layernorm_after/vars": [
|
| 535 |
+
"model_00000.weights.h5"
|
| 536 |
+
],
|
| 537 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/layernorm_before/vars": [
|
| 538 |
+
"model_00000.weights.h5"
|
| 539 |
+
],
|
| 540 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/mlp/fc1/vars": [
|
| 541 |
+
"model_00000.weights.h5"
|
| 542 |
+
],
|
| 543 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_19/mlp/fc2/vars": [
|
| 544 |
+
"model_00000.weights.h5"
|
| 545 |
+
],
|
| 546 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/vars": [
|
| 547 |
+
"model_00000.weights.h5"
|
| 548 |
+
],
|
| 549 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/attention/key/vars": [
|
| 550 |
+
"model_00000.weights.h5"
|
| 551 |
+
],
|
| 552 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/attention/output_proj/vars": [
|
| 553 |
+
"model_00000.weights.h5"
|
| 554 |
+
],
|
| 555 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/attention/query/vars": [
|
| 556 |
+
"model_00000.weights.h5"
|
| 557 |
+
],
|
| 558 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/attention/value/vars": [
|
| 559 |
+
"model_00000.weights.h5"
|
| 560 |
+
],
|
| 561 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/layernorm_after/vars": [
|
| 562 |
+
"model_00000.weights.h5"
|
| 563 |
+
],
|
| 564 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/layernorm_before/vars": [
|
| 565 |
+
"model_00000.weights.h5"
|
| 566 |
+
],
|
| 567 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/mlp/fc1/vars": [
|
| 568 |
+
"model_00000.weights.h5"
|
| 569 |
+
],
|
| 570 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_20/mlp/fc2/vars": [
|
| 571 |
+
"model_00000.weights.h5"
|
| 572 |
+
],
|
| 573 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/vars": [
|
| 574 |
+
"model_00000.weights.h5"
|
| 575 |
+
],
|
| 576 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/attention/key/vars": [
|
| 577 |
+
"model_00000.weights.h5"
|
| 578 |
+
],
|
| 579 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/attention/output_proj/vars": [
|
| 580 |
+
"model_00000.weights.h5"
|
| 581 |
+
],
|
| 582 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/attention/query/vars": [
|
| 583 |
+
"model_00000.weights.h5"
|
| 584 |
+
],
|
| 585 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/attention/value/vars": [
|
| 586 |
+
"model_00000.weights.h5"
|
| 587 |
+
],
|
| 588 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/layernorm_after/vars": [
|
| 589 |
+
"model_00000.weights.h5"
|
| 590 |
+
],
|
| 591 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/layernorm_before/vars": [
|
| 592 |
+
"model_00000.weights.h5"
|
| 593 |
+
],
|
| 594 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/mlp/fc1/vars": [
|
| 595 |
+
"model_00000.weights.h5"
|
| 596 |
+
],
|
| 597 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_21/mlp/fc2/vars": [
|
| 598 |
+
"model_00000.weights.h5"
|
| 599 |
+
],
|
| 600 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/vars": [
|
| 601 |
+
"model_00000.weights.h5"
|
| 602 |
+
],
|
| 603 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/attention/key/vars": [
|
| 604 |
+
"model_00000.weights.h5"
|
| 605 |
+
],
|
| 606 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/attention/output_proj/vars": [
|
| 607 |
+
"model_00000.weights.h5"
|
| 608 |
+
],
|
| 609 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/attention/query/vars": [
|
| 610 |
+
"model_00000.weights.h5"
|
| 611 |
+
],
|
| 612 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/attention/value/vars": [
|
| 613 |
+
"model_00000.weights.h5"
|
| 614 |
+
],
|
| 615 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/layernorm_after/vars": [
|
| 616 |
+
"model_00000.weights.h5"
|
| 617 |
+
],
|
| 618 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/layernorm_before/vars": [
|
| 619 |
+
"model_00000.weights.h5"
|
| 620 |
+
],
|
| 621 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/mlp/fc1/vars": [
|
| 622 |
+
"model_00000.weights.h5"
|
| 623 |
+
],
|
| 624 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_22/mlp/fc2/vars": [
|
| 625 |
+
"model_00000.weights.h5"
|
| 626 |
+
],
|
| 627 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/vars": [
|
| 628 |
+
"model_00000.weights.h5"
|
| 629 |
+
],
|
| 630 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/attention/key/vars": [
|
| 631 |
+
"model_00000.weights.h5"
|
| 632 |
+
],
|
| 633 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/attention/output_proj/vars": [
|
| 634 |
+
"model_00000.weights.h5"
|
| 635 |
+
],
|
| 636 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/attention/query/vars": [
|
| 637 |
+
"model_00000.weights.h5"
|
| 638 |
+
],
|
| 639 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/attention/value/vars": [
|
| 640 |
+
"model_00000.weights.h5"
|
| 641 |
+
],
|
| 642 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/layernorm_after/vars": [
|
| 643 |
+
"model_00000.weights.h5"
|
| 644 |
+
],
|
| 645 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/layernorm_before/vars": [
|
| 646 |
+
"model_00000.weights.h5"
|
| 647 |
+
],
|
| 648 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/mlp/fc1/vars": [
|
| 649 |
+
"model_00000.weights.h5"
|
| 650 |
+
],
|
| 651 |
+
"/layers/intern_vl_vision_model/blocks/intern_vl_vision_layer_23/mlp/fc2/vars": [
|
| 652 |
+
"model_00000.weights.h5"
|
| 653 |
+
],
|
| 654 |
+
"/layers/intern_vl_vision_model/embeddings/vars": [
|
| 655 |
+
"model_00000.weights.h5"
|
| 656 |
+
],
|
| 657 |
+
"/layers/intern_vl_vision_model/embeddings/patch_embed/vars": [
|
| 658 |
+
"model_00000.weights.h5"
|
| 659 |
+
],
|
| 660 |
+
"/layers/embedding/vars": "model_00000.weights.h5",
|
| 661 |
+
"/layers/intern_vl_multi_modal_projector/layer_norm/vars": [
|
| 662 |
+
"model_00000.weights.h5"
|
| 663 |
+
],
|
| 664 |
+
"/layers/intern_vl_multi_modal_projector/linear_1/vars": [
|
| 665 |
+
"model_00000.weights.h5"
|
| 666 |
+
],
|
| 667 |
+
"/layers/intern_vl_multi_modal_projector/linear_2/vars": [
|
| 668 |
+
"model_00000.weights.h5"
|
| 669 |
+
],
|
| 670 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention/key/vars": "model_00000.weights.h5",
|
| 671 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention/key_norm/vars": "model_00000.weights.h5",
|
| 672 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention/output_proj/vars": "model_00000.weights.h5",
|
| 673 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention/query/vars": "model_00000.weights.h5",
|
| 674 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention/query_norm/vars": "model_00000.weights.h5",
|
| 675 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention/value/vars": "model_00000.weights.h5",
|
| 676 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/attention_norm/vars": "model_00000.weights.h5",
|
| 677 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/mlp/down/vars": "model_00000.weights.h5",
|
| 678 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/mlp/gate/vars": "model_00000.weights.h5",
|
| 679 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/mlp/up/vars": "model_00000.weights.h5",
|
| 680 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer/mlp_norm/vars": "model_00000.weights.h5",
|
| 681 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention/key/vars": "model_00000.weights.h5",
|
| 682 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention/key_norm/vars": "model_00000.weights.h5",
|
| 683 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention/output_proj/vars": "model_00000.weights.h5",
|
| 684 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention/query/vars": "model_00000.weights.h5",
|
| 685 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention/query_norm/vars": "model_00000.weights.h5",
|
| 686 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention/value/vars": "model_00000.weights.h5",
|
| 687 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/attention_norm/vars": "model_00000.weights.h5",
|
| 688 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/mlp/down/vars": "model_00000.weights.h5",
|
| 689 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/mlp/gate/vars": "model_00000.weights.h5",
|
| 690 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/mlp/up/vars": "model_00000.weights.h5",
|
| 691 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_1/mlp_norm/vars": "model_00000.weights.h5",
|
| 692 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention/key/vars": "model_00000.weights.h5",
|
| 693 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention/key_norm/vars": "model_00000.weights.h5",
|
| 694 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention/output_proj/vars": "model_00000.weights.h5",
|
| 695 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention/query/vars": "model_00000.weights.h5",
|
| 696 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention/query_norm/vars": "model_00000.weights.h5",
|
| 697 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention/value/vars": "model_00000.weights.h5",
|
| 698 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/attention_norm/vars": "model_00000.weights.h5",
|
| 699 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/mlp/down/vars": "model_00000.weights.h5",
|
| 700 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/mlp/gate/vars": "model_00000.weights.h5",
|
| 701 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/mlp/up/vars": "model_00000.weights.h5",
|
| 702 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_2/mlp_norm/vars": "model_00000.weights.h5",
|
| 703 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention/key/vars": "model_00000.weights.h5",
|
| 704 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention/key_norm/vars": "model_00000.weights.h5",
|
| 705 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention/output_proj/vars": "model_00000.weights.h5",
|
| 706 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention/query/vars": "model_00000.weights.h5",
|
| 707 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention/query_norm/vars": "model_00000.weights.h5",
|
| 708 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention/value/vars": "model_00000.weights.h5",
|
| 709 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/attention_norm/vars": "model_00000.weights.h5",
|
| 710 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/mlp/down/vars": "model_00000.weights.h5",
|
| 711 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/mlp/gate/vars": "model_00000.weights.h5",
|
| 712 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/mlp/up/vars": "model_00000.weights.h5",
|
| 713 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_3/mlp_norm/vars": "model_00000.weights.h5",
|
| 714 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention/key/vars": "model_00000.weights.h5",
|
| 715 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention/key_norm/vars": "model_00000.weights.h5",
|
| 716 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention/output_proj/vars": "model_00000.weights.h5",
|
| 717 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention/query/vars": "model_00000.weights.h5",
|
| 718 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention/query_norm/vars": "model_00000.weights.h5",
|
| 719 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention/value/vars": "model_00000.weights.h5",
|
| 720 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/attention_norm/vars": "model_00000.weights.h5",
|
| 721 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/mlp/down/vars": "model_00000.weights.h5",
|
| 722 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/mlp/gate/vars": "model_00000.weights.h5",
|
| 723 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/mlp/up/vars": "model_00000.weights.h5",
|
| 724 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_4/mlp_norm/vars": "model_00000.weights.h5",
|
| 725 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention/key/vars": "model_00000.weights.h5",
|
| 726 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention/key_norm/vars": "model_00000.weights.h5",
|
| 727 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention/output_proj/vars": "model_00000.weights.h5",
|
| 728 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention/query/vars": "model_00000.weights.h5",
|
| 729 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention/query_norm/vars": "model_00000.weights.h5",
|
| 730 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention/value/vars": "model_00000.weights.h5",
|
| 731 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/attention_norm/vars": "model_00000.weights.h5",
|
| 732 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/mlp/down/vars": "model_00000.weights.h5",
|
| 733 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/mlp/gate/vars": "model_00000.weights.h5",
|
| 734 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/mlp/up/vars": "model_00000.weights.h5",
|
| 735 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_5/mlp_norm/vars": "model_00000.weights.h5",
|
| 736 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention/key/vars": "model_00000.weights.h5",
|
| 737 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention/key_norm/vars": "model_00000.weights.h5",
|
| 738 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention/output_proj/vars": "model_00000.weights.h5",
|
| 739 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention/query/vars": "model_00000.weights.h5",
|
| 740 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention/query_norm/vars": "model_00000.weights.h5",
|
| 741 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention/value/vars": "model_00000.weights.h5",
|
| 742 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/attention_norm/vars": "model_00000.weights.h5",
|
| 743 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/mlp/down/vars": "model_00000.weights.h5",
|
| 744 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/mlp/gate/vars": "model_00000.weights.h5",
|
| 745 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/mlp/up/vars": "model_00000.weights.h5",
|
| 746 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_6/mlp_norm/vars": "model_00000.weights.h5",
|
| 747 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention/key/vars": "model_00000.weights.h5",
|
| 748 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention/key_norm/vars": "model_00000.weights.h5",
|
| 749 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention/output_proj/vars": "model_00000.weights.h5",
|
| 750 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention/query/vars": "model_00000.weights.h5",
|
| 751 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention/query_norm/vars": "model_00000.weights.h5",
|
| 752 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention/value/vars": "model_00000.weights.h5",
|
| 753 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/attention_norm/vars": "model_00000.weights.h5",
|
| 754 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/mlp/down/vars": "model_00000.weights.h5",
|
| 755 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/mlp/gate/vars": "model_00000.weights.h5",
|
| 756 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/mlp/up/vars": "model_00000.weights.h5",
|
| 757 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_7/mlp_norm/vars": "model_00000.weights.h5",
|
| 758 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention/key/vars": "model_00000.weights.h5",
|
| 759 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention/key_norm/vars": "model_00000.weights.h5",
|
| 760 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention/output_proj/vars": "model_00000.weights.h5",
|
| 761 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention/query/vars": "model_00000.weights.h5",
|
| 762 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention/query_norm/vars": "model_00000.weights.h5",
|
| 763 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention/value/vars": "model_00000.weights.h5",
|
| 764 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/attention_norm/vars": "model_00000.weights.h5",
|
| 765 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/mlp/down/vars": "model_00000.weights.h5",
|
| 766 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/mlp/gate/vars": "model_00000.weights.h5",
|
| 767 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/mlp/up/vars": "model_00000.weights.h5",
|
| 768 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_8/mlp_norm/vars": "model_00000.weights.h5",
|
| 769 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention/key/vars": "model_00000.weights.h5",
|
| 770 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention/key_norm/vars": "model_00000.weights.h5",
|
| 771 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention/output_proj/vars": "model_00000.weights.h5",
|
| 772 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention/query/vars": "model_00000.weights.h5",
|
| 773 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention/query_norm/vars": "model_00000.weights.h5",
|
| 774 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention/value/vars": "model_00000.weights.h5",
|
| 775 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/attention_norm/vars": "model_00000.weights.h5",
|
| 776 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/mlp/down/vars": "model_00000.weights.h5",
|
| 777 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/mlp/gate/vars": "model_00000.weights.h5",
|
| 778 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/mlp/up/vars": "model_00000.weights.h5",
|
| 779 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_9/mlp_norm/vars": "model_00000.weights.h5",
|
| 780 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention/key/vars": "model_00000.weights.h5",
|
| 781 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention/key_norm/vars": "model_00000.weights.h5",
|
| 782 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention/output_proj/vars": "model_00000.weights.h5",
|
| 783 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention/query/vars": "model_00000.weights.h5",
|
| 784 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention/query_norm/vars": "model_00000.weights.h5",
|
| 785 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention/value/vars": "model_00000.weights.h5",
|
| 786 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/attention_norm/vars": "model_00000.weights.h5",
|
| 787 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/mlp/down/vars": "model_00000.weights.h5",
|
| 788 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/mlp/gate/vars": "model_00000.weights.h5",
|
| 789 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/mlp/up/vars": "model_00000.weights.h5",
|
| 790 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_10/mlp_norm/vars": "model_00000.weights.h5",
|
| 791 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention/key/vars": "model_00000.weights.h5",
|
| 792 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention/key_norm/vars": "model_00000.weights.h5",
|
| 793 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention/output_proj/vars": "model_00000.weights.h5",
|
| 794 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention/query/vars": "model_00000.weights.h5",
|
| 795 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention/query_norm/vars": "model_00000.weights.h5",
|
| 796 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention/value/vars": "model_00000.weights.h5",
|
| 797 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/attention_norm/vars": "model_00000.weights.h5",
|
| 798 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/mlp/down/vars": "model_00000.weights.h5",
|
| 799 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/mlp/gate/vars": "model_00000.weights.h5",
|
| 800 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/mlp/up/vars": "model_00000.weights.h5",
|
| 801 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_11/mlp_norm/vars": "model_00000.weights.h5",
|
| 802 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention/key/vars": "model_00000.weights.h5",
|
| 803 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention/key_norm/vars": "model_00000.weights.h5",
|
| 804 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention/output_proj/vars": "model_00000.weights.h5",
|
| 805 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention/query/vars": "model_00000.weights.h5",
|
| 806 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention/query_norm/vars": "model_00000.weights.h5",
|
| 807 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention/value/vars": "model_00000.weights.h5",
|
| 808 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/attention_norm/vars": "model_00000.weights.h5",
|
| 809 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/mlp/down/vars": "model_00000.weights.h5",
|
| 810 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/mlp/gate/vars": "model_00000.weights.h5",
|
| 811 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/mlp/up/vars": "model_00000.weights.h5",
|
| 812 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_12/mlp_norm/vars": "model_00000.weights.h5",
|
| 813 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention/key/vars": "model_00000.weights.h5",
|
| 814 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention/key_norm/vars": "model_00000.weights.h5",
|
| 815 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention/output_proj/vars": "model_00000.weights.h5",
|
| 816 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention/query/vars": "model_00000.weights.h5",
|
| 817 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention/query_norm/vars": "model_00000.weights.h5",
|
| 818 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention/value/vars": "model_00000.weights.h5",
|
| 819 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/attention_norm/vars": "model_00000.weights.h5",
|
| 820 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/mlp/down/vars": "model_00000.weights.h5",
|
| 821 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/mlp/gate/vars": "model_00000.weights.h5",
|
| 822 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/mlp/up/vars": "model_00000.weights.h5",
|
| 823 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_13/mlp_norm/vars": "model_00000.weights.h5",
|
| 824 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention/key/vars": "model_00000.weights.h5",
|
| 825 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention/key_norm/vars": "model_00000.weights.h5",
|
| 826 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention/output_proj/vars": "model_00000.weights.h5",
|
| 827 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention/query/vars": "model_00000.weights.h5",
|
| 828 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention/query_norm/vars": "model_00000.weights.h5",
|
| 829 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention/value/vars": "model_00000.weights.h5",
|
| 830 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/attention_norm/vars": "model_00000.weights.h5",
|
| 831 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/mlp/down/vars": "model_00000.weights.h5",
|
| 832 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/mlp/gate/vars": "model_00000.weights.h5",
|
| 833 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/mlp/up/vars": "model_00000.weights.h5",
|
| 834 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_14/mlp_norm/vars": "model_00000.weights.h5",
|
| 835 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention/key/vars": "model_00000.weights.h5",
|
| 836 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention/key_norm/vars": "model_00000.weights.h5",
|
| 837 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention/output_proj/vars": "model_00000.weights.h5",
|
| 838 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention/query/vars": "model_00000.weights.h5",
|
| 839 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention/query_norm/vars": "model_00000.weights.h5",
|
| 840 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention/value/vars": "model_00000.weights.h5",
|
| 841 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/attention_norm/vars": "model_00000.weights.h5",
|
| 842 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/mlp/down/vars": "model_00000.weights.h5",
|
| 843 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/mlp/gate/vars": "model_00000.weights.h5",
|
| 844 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/mlp/up/vars": "model_00000.weights.h5",
|
| 845 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_15/mlp_norm/vars": "model_00000.weights.h5",
|
| 846 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention/key/vars": "model_00000.weights.h5",
|
| 847 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention/key_norm/vars": "model_00000.weights.h5",
|
| 848 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention/output_proj/vars": "model_00000.weights.h5",
|
| 849 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention/query/vars": "model_00000.weights.h5",
|
| 850 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention/query_norm/vars": "model_00000.weights.h5",
|
| 851 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention/value/vars": "model_00000.weights.h5",
|
| 852 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/attention_norm/vars": "model_00000.weights.h5",
|
| 853 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/mlp/down/vars": "model_00000.weights.h5",
|
| 854 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/mlp/gate/vars": "model_00000.weights.h5",
|
| 855 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/mlp/up/vars": "model_00000.weights.h5",
|
| 856 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_16/mlp_norm/vars": "model_00000.weights.h5",
|
| 857 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention/key/vars": "model_00000.weights.h5",
|
| 858 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention/key_norm/vars": "model_00000.weights.h5",
|
| 859 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention/output_proj/vars": "model_00000.weights.h5",
|
| 860 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention/query/vars": "model_00000.weights.h5",
|
| 861 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention/query_norm/vars": "model_00000.weights.h5",
|
| 862 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention/value/vars": "model_00000.weights.h5",
|
| 863 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/attention_norm/vars": "model_00000.weights.h5",
|
| 864 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/mlp/down/vars": "model_00000.weights.h5",
|
| 865 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/mlp/gate/vars": "model_00000.weights.h5",
|
| 866 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/mlp/up/vars": "model_00000.weights.h5",
|
| 867 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_17/mlp_norm/vars": "model_00000.weights.h5",
|
| 868 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention/key/vars": "model_00000.weights.h5",
|
| 869 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention/key_norm/vars": "model_00000.weights.h5",
|
| 870 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention/output_proj/vars": "model_00000.weights.h5",
|
| 871 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention/query/vars": "model_00000.weights.h5",
|
| 872 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention/query_norm/vars": "model_00000.weights.h5",
|
| 873 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention/value/vars": "model_00000.weights.h5",
|
| 874 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/attention_norm/vars": "model_00000.weights.h5",
|
| 875 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/mlp/down/vars": "model_00000.weights.h5",
|
| 876 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/mlp/gate/vars": "model_00000.weights.h5",
|
| 877 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/mlp/up/vars": "model_00000.weights.h5",
|
| 878 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_18/mlp_norm/vars": "model_00000.weights.h5",
|
| 879 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention/key/vars": "model_00000.weights.h5",
|
| 880 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention/key_norm/vars": "model_00000.weights.h5",
|
| 881 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention/output_proj/vars": "model_00000.weights.h5",
|
| 882 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention/query/vars": "model_00000.weights.h5",
|
| 883 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention/query_norm/vars": "model_00000.weights.h5",
|
| 884 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention/value/vars": "model_00000.weights.h5",
|
| 885 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/attention_norm/vars": "model_00000.weights.h5",
|
| 886 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/mlp/down/vars": "model_00000.weights.h5",
|
| 887 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/mlp/gate/vars": "model_00001.weights.h5",
|
| 888 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/mlp/up/vars": "model_00001.weights.h5",
|
| 889 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_19/mlp_norm/vars": "model_00001.weights.h5",
|
| 890 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention/key/vars": "model_00001.weights.h5",
|
| 891 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention/key_norm/vars": "model_00001.weights.h5",
|
| 892 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention/output_proj/vars": "model_00001.weights.h5",
|
| 893 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention/query/vars": "model_00001.weights.h5",
|
| 894 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention/query_norm/vars": "model_00001.weights.h5",
|
| 895 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention/value/vars": "model_00001.weights.h5",
|
| 896 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/attention_norm/vars": "model_00001.weights.h5",
|
| 897 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/mlp/down/vars": "model_00001.weights.h5",
|
| 898 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/mlp/gate/vars": "model_00001.weights.h5",
|
| 899 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/mlp/up/vars": "model_00001.weights.h5",
|
| 900 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_20/mlp_norm/vars": "model_00001.weights.h5",
|
| 901 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention/key/vars": "model_00001.weights.h5",
|
| 902 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention/key_norm/vars": "model_00001.weights.h5",
|
| 903 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention/output_proj/vars": "model_00001.weights.h5",
|
| 904 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention/query/vars": "model_00001.weights.h5",
|
| 905 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention/query_norm/vars": "model_00001.weights.h5",
|
| 906 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention/value/vars": "model_00001.weights.h5",
|
| 907 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/attention_norm/vars": "model_00001.weights.h5",
|
| 908 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/mlp/down/vars": "model_00001.weights.h5",
|
| 909 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/mlp/gate/vars": "model_00001.weights.h5",
|
| 910 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/mlp/up/vars": "model_00001.weights.h5",
|
| 911 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_21/mlp_norm/vars": "model_00001.weights.h5",
|
| 912 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention/key/vars": "model_00001.weights.h5",
|
| 913 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention/key_norm/vars": "model_00001.weights.h5",
|
| 914 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention/output_proj/vars": "model_00001.weights.h5",
|
| 915 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention/query/vars": "model_00001.weights.h5",
|
| 916 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention/query_norm/vars": "model_00001.weights.h5",
|
| 917 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention/value/vars": "model_00001.weights.h5",
|
| 918 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/attention_norm/vars": "model_00001.weights.h5",
|
| 919 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/mlp/down/vars": "model_00001.weights.h5",
|
| 920 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/mlp/gate/vars": "model_00001.weights.h5",
|
| 921 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/mlp/up/vars": "model_00001.weights.h5",
|
| 922 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_22/mlp_norm/vars": "model_00001.weights.h5",
|
| 923 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention/key/vars": "model_00001.weights.h5",
|
| 924 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention/key_norm/vars": "model_00001.weights.h5",
|
| 925 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention/output_proj/vars": "model_00001.weights.h5",
|
| 926 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention/query/vars": "model_00001.weights.h5",
|
| 927 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention/query_norm/vars": "model_00001.weights.h5",
|
| 928 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention/value/vars": "model_00001.weights.h5",
|
| 929 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/attention_norm/vars": "model_00001.weights.h5",
|
| 930 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/mlp/down/vars": "model_00001.weights.h5",
|
| 931 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/mlp/gate/vars": "model_00001.weights.h5",
|
| 932 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/mlp/up/vars": "model_00001.weights.h5",
|
| 933 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_23/mlp_norm/vars": "model_00001.weights.h5",
|
| 934 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention/key/vars": "model_00001.weights.h5",
|
| 935 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention/key_norm/vars": "model_00001.weights.h5",
|
| 936 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention/output_proj/vars": "model_00001.weights.h5",
|
| 937 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention/query/vars": "model_00001.weights.h5",
|
| 938 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention/query_norm/vars": "model_00001.weights.h5",
|
| 939 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention/value/vars": "model_00001.weights.h5",
|
| 940 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/attention_norm/vars": "model_00001.weights.h5",
|
| 941 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/mlp/down/vars": "model_00001.weights.h5",
|
| 942 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/mlp/gate/vars": "model_00001.weights.h5",
|
| 943 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/mlp/up/vars": "model_00001.weights.h5",
|
| 944 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_24/mlp_norm/vars": "model_00001.weights.h5",
|
| 945 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention/key/vars": "model_00001.weights.h5",
|
| 946 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention/key_norm/vars": "model_00001.weights.h5",
|
| 947 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention/output_proj/vars": "model_00001.weights.h5",
|
| 948 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention/query/vars": "model_00001.weights.h5",
|
| 949 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention/query_norm/vars": "model_00001.weights.h5",
|
| 950 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention/value/vars": "model_00001.weights.h5",
|
| 951 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/attention_norm/vars": "model_00001.weights.h5",
|
| 952 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/mlp/down/vars": "model_00001.weights.h5",
|
| 953 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/mlp/gate/vars": "model_00001.weights.h5",
|
| 954 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/mlp/up/vars": "model_00001.weights.h5",
|
| 955 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_25/mlp_norm/vars": "model_00001.weights.h5",
|
| 956 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention/key/vars": "model_00001.weights.h5",
|
| 957 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention/key_norm/vars": "model_00001.weights.h5",
|
| 958 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention/output_proj/vars": "model_00001.weights.h5",
|
| 959 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention/query/vars": "model_00001.weights.h5",
|
| 960 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention/query_norm/vars": "model_00001.weights.h5",
|
| 961 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention/value/vars": "model_00001.weights.h5",
|
| 962 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/attention_norm/vars": "model_00001.weights.h5",
|
| 963 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/mlp/down/vars": "model_00001.weights.h5",
|
| 964 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/mlp/gate/vars": "model_00001.weights.h5",
|
| 965 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/mlp/up/vars": "model_00001.weights.h5",
|
| 966 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_26/mlp_norm/vars": "model_00001.weights.h5",
|
| 967 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention/key/vars": "model_00001.weights.h5",
|
| 968 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention/key_norm/vars": "model_00001.weights.h5",
|
| 969 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention/output_proj/vars": "model_00001.weights.h5",
|
| 970 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention/query/vars": "model_00001.weights.h5",
|
| 971 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention/query_norm/vars": "model_00001.weights.h5",
|
| 972 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention/value/vars": "model_00001.weights.h5",
|
| 973 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/attention_norm/vars": "model_00001.weights.h5",
|
| 974 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/mlp/down/vars": "model_00001.weights.h5",
|
| 975 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/mlp/gate/vars": "model_00001.weights.h5",
|
| 976 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/mlp/up/vars": "model_00001.weights.h5",
|
| 977 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_27/mlp_norm/vars": "model_00001.weights.h5",
|
| 978 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention/key/vars": "model_00001.weights.h5",
|
| 979 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention/key_norm/vars": "model_00001.weights.h5",
|
| 980 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention/output_proj/vars": "model_00001.weights.h5",
|
| 981 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention/query/vars": "model_00001.weights.h5",
|
| 982 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention/query_norm/vars": "model_00001.weights.h5",
|
| 983 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention/value/vars": "model_00001.weights.h5",
|
| 984 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/attention_norm/vars": "model_00001.weights.h5",
|
| 985 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/mlp/down/vars": "model_00001.weights.h5",
|
| 986 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/mlp/gate/vars": "model_00001.weights.h5",
|
| 987 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/mlp/up/vars": "model_00001.weights.h5",
|
| 988 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_28/mlp_norm/vars": "model_00001.weights.h5",
|
| 989 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention/key/vars": "model_00001.weights.h5",
|
| 990 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention/key_norm/vars": "model_00001.weights.h5",
|
| 991 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention/output_proj/vars": "model_00001.weights.h5",
|
| 992 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention/query/vars": "model_00001.weights.h5",
|
| 993 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention/query_norm/vars": "model_00001.weights.h5",
|
| 994 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention/value/vars": "model_00001.weights.h5",
|
| 995 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/attention_norm/vars": "model_00001.weights.h5",
|
| 996 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/mlp/down/vars": "model_00001.weights.h5",
|
| 997 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/mlp/gate/vars": "model_00001.weights.h5",
|
| 998 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/mlp/up/vars": "model_00001.weights.h5",
|
| 999 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_29/mlp_norm/vars": "model_00001.weights.h5",
|
| 1000 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention/key/vars": "model_00001.weights.h5",
|
| 1001 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention/key_norm/vars": "model_00001.weights.h5",
|
| 1002 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention/output_proj/vars": "model_00001.weights.h5",
|
| 1003 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention/query/vars": "model_00001.weights.h5",
|
| 1004 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention/query_norm/vars": "model_00001.weights.h5",
|
| 1005 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention/value/vars": "model_00001.weights.h5",
|
| 1006 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/attention_norm/vars": "model_00001.weights.h5",
|
| 1007 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/mlp/down/vars": "model_00001.weights.h5",
|
| 1008 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/mlp/gate/vars": "model_00001.weights.h5",
|
| 1009 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/mlp/up/vars": "model_00001.weights.h5",
|
| 1010 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_30/mlp_norm/vars": "model_00001.weights.h5",
|
| 1011 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention/key/vars": "model_00001.weights.h5",
|
| 1012 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention/key_norm/vars": "model_00001.weights.h5",
|
| 1013 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention/output_proj/vars": "model_00001.weights.h5",
|
| 1014 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention/query/vars": "model_00001.weights.h5",
|
| 1015 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention/query_norm/vars": "model_00001.weights.h5",
|
| 1016 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention/value/vars": "model_00001.weights.h5",
|
| 1017 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/attention_norm/vars": "model_00001.weights.h5",
|
| 1018 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/mlp/down/vars": "model_00001.weights.h5",
|
| 1019 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/mlp/gate/vars": "model_00001.weights.h5",
|
| 1020 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/mlp/up/vars": "model_00001.weights.h5",
|
| 1021 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_31/mlp_norm/vars": "model_00001.weights.h5",
|
| 1022 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention/key/vars": "model_00001.weights.h5",
|
| 1023 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention/key_norm/vars": "model_00001.weights.h5",
|
| 1024 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention/output_proj/vars": "model_00001.weights.h5",
|
| 1025 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention/query/vars": "model_00001.weights.h5",
|
| 1026 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention/query_norm/vars": "model_00001.weights.h5",
|
| 1027 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention/value/vars": "model_00001.weights.h5",
|
| 1028 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/attention_norm/vars": "model_00001.weights.h5",
|
| 1029 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/mlp/down/vars": "model_00001.weights.h5",
|
| 1030 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/mlp/gate/vars": "model_00001.weights.h5",
|
| 1031 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/mlp/up/vars": "model_00001.weights.h5",
|
| 1032 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_32/mlp_norm/vars": "model_00001.weights.h5",
|
| 1033 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention/key/vars": "model_00001.weights.h5",
|
| 1034 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention/key_norm/vars": "model_00001.weights.h5",
|
| 1035 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention/output_proj/vars": "model_00001.weights.h5",
|
| 1036 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention/query/vars": "model_00001.weights.h5",
|
| 1037 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention/query_norm/vars": "model_00001.weights.h5",
|
| 1038 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention/value/vars": "model_00001.weights.h5",
|
| 1039 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/attention_norm/vars": "model_00001.weights.h5",
|
| 1040 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/mlp/down/vars": "model_00001.weights.h5",
|
| 1041 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/mlp/gate/vars": "model_00001.weights.h5",
|
| 1042 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/mlp/up/vars": "model_00001.weights.h5",
|
| 1043 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_33/mlp_norm/vars": "model_00001.weights.h5",
|
| 1044 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention/key/vars": "model_00001.weights.h5",
|
| 1045 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention/key_norm/vars": "model_00001.weights.h5",
|
| 1046 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention/output_proj/vars": "model_00001.weights.h5",
|
| 1047 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention/query/vars": "model_00001.weights.h5",
|
| 1048 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention/query_norm/vars": "model_00001.weights.h5",
|
| 1049 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention/value/vars": "model_00001.weights.h5",
|
| 1050 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/attention_norm/vars": "model_00001.weights.h5",
|
| 1051 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/mlp/down/vars": "model_00001.weights.h5",
|
| 1052 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/mlp/gate/vars": "model_00001.weights.h5",
|
| 1053 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/mlp/up/vars": "model_00001.weights.h5",
|
| 1054 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_34/mlp_norm/vars": "model_00001.weights.h5",
|
| 1055 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention/key/vars": "model_00001.weights.h5",
|
| 1056 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention/key_norm/vars": "model_00001.weights.h5",
|
| 1057 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention/output_proj/vars": "model_00001.weights.h5",
|
| 1058 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention/query/vars": "model_00001.weights.h5",
|
| 1059 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention/query_norm/vars": "model_00001.weights.h5",
|
| 1060 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention/value/vars": "model_00001.weights.h5",
|
| 1061 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/attention_norm/vars": "model_00001.weights.h5",
|
| 1062 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/mlp/down/vars": "model_00001.weights.h5",
|
| 1063 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/mlp/gate/vars": "model_00001.weights.h5",
|
| 1064 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/mlp/up/vars": "model_00001.weights.h5",
|
| 1065 |
+
"/layers/intern_vl_text_model/decoder_layers/intern_vl_decoder_layer_35/mlp_norm/vars": "model_00001.weights.h5",
|
| 1066 |
+
"/layers/intern_vl_text_model/final_norm/vars": "model_00001.weights.h5",
|
| 1067 |
+
"/layers/dense/vars": "model_00001.weights.h5"
|
| 1068 |
+
}
|
| 1069 |
+
}
|
model_00000.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:269caa94f1cd9fdf44e5060c17f1d55c258f11ddc46cc76a0aaad9971e38934a
|
| 3 |
+
size 5359045584
|
model_00001.weights.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c271c536b661d9d74f47162a0e82d319cdf21c0ba7d2e00062867f1020312093
|
| 3 |
+
size 4107873192
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b9d18660f656ae5a87df2d5d6ed990e80f292d3473c1a35cae8259a5d28cd67
|
| 3 |
+
size 11424484
|