Add sapiens2-seg-0.4b-5bit
Browse files- README.md +95 -0
- config.json +67 -0
- model.safetensors +3 -0
- model.safetensors.index.json +719 -0
- preprocessor_config.json +16 -0
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: sapiens2-license
|
| 4 |
+
license_link: https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md
|
| 5 |
+
library_name: mlx
|
| 6 |
+
tags:
|
| 7 |
+
- mlx
|
| 8 |
+
- sapiens2
|
| 9 |
+
- vision
|
| 10 |
+
- human-centric
|
| 11 |
+
- seg
|
| 12 |
+
pipeline_tag: image-to-image
|
| 13 |
+
base_model:
|
| 14 |
+
- facebook/sapiens2-seg-0.4b
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# mlx-community/sapiens2-seg-0.4b-5bit
|
| 18 |
+
|
| 19 |
+
MLX port of [`facebook/sapiens2-seg-0.4b`](https://huggingface.co/facebook/sapiens2-seg-0.4b) at **5-bit affine (group_size=64)** precision, converted with [mlx-vlm](https://github.com/Blaizzy/mlx-vlm).
|
| 20 |
+
|
| 21 |
+
Sapiens2 is a family of human-centric ViTs pretrained on 1B human images. This
|
| 22 |
+
repo contains the **seg** head paired with the Sapiens2-0.4b backbone.
|
| 23 |
+
|
| 24 |
+
## Install
|
| 25 |
+
|
| 26 |
+
```bash
|
| 27 |
+
pip install -U mlx-vlm
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
## Usage — body-part segmentation (29 classes)
|
| 31 |
+
|
| 32 |
+
```python
|
| 33 |
+
from pathlib import Path
|
| 34 |
+
from PIL import Image
|
| 35 |
+
import numpy as np
|
| 36 |
+
from mlx_vlm.utils import load_model
|
| 37 |
+
from mlx_vlm.models.sapiens2.processing_sapiens2 import Sapiens2Processor
|
| 38 |
+
from mlx_vlm.models.sapiens2.generate import Sapiens2Predictor
|
| 39 |
+
|
| 40 |
+
model = load_model(Path("mlx-community/sapiens2-seg-0.4b-5bit"))
|
| 41 |
+
processor = Sapiens2Processor.from_pretrained("mlx-community/sapiens2-seg-0.4b-5bit")
|
| 42 |
+
predictor = Sapiens2Predictor(model, processor)
|
| 43 |
+
|
| 44 |
+
result = predictor.predict(Image.open("person.jpg"))
|
| 45 |
+
# result.mask (orig_h, orig_w) int32 class indices
|
| 46 |
+
# result.seg_logits (29, H_out, W_out) raw logits
|
| 47 |
+
|
| 48 |
+
print("active classes:", np.unique(result.mask).tolist())
|
| 49 |
+
Image.fromarray(result.mask.astype(np.uint8)).save("mask.png")
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
Output: dense 29-class body-part segmentation (DOME 29-class scheme — face,
|
| 53 |
+
hair, torso, arms/legs split left/right, etc.).
|
| 54 |
+
|
| 55 |
+
## Convert your own checkpoint
|
| 56 |
+
|
| 57 |
+
```bash
|
| 58 |
+
# 1. Stage a float32 MLX directory from the Facebook checkpoint
|
| 59 |
+
python -m mlx_vlm.models.sapiens2.convert \
|
| 60 |
+
--hf-repo facebook/sapiens2-seg-0.4b \
|
| 61 |
+
--out ./sapiens2-seg-0.4b-fp32-mlx \
|
| 62 |
+
--dtype float32
|
| 63 |
+
|
| 64 |
+
# 2. Quantize + upload via the main mlx_vlm.convert CLI
|
| 65 |
+
python -m mlx_vlm.convert \
|
| 66 |
+
--hf-path ./sapiens2-seg-0.4b-fp32-mlx \
|
| 67 |
+
--mlx-path ./sapiens2-seg-0.4b-5bit \
|
| 68 |
+
--quantize --q-bits 5 --q-group-size 64 --q-mode affine \
|
| 69 |
+
--upload-repo mlx-community/sapiens2-seg-0.4b-5bit
|
| 70 |
+
```
|
| 71 |
+
|
| 72 |
+
## Architecture
|
| 73 |
+
|
| 74 |
+
Sapiens2 backbone: 2-D RoPE ViT (bf16 rope), partial GQA (full MHA in the
|
| 75 |
+
first/last 8 blocks, KV-half for the middle), SwiGLU FFN, cls + 8 storage
|
| 76 |
+
tokens. Default input: **1024 × 768 (H × W)**, patch size 16, ImageNet
|
| 77 |
+
normalization on the [0, 255] scale.
|
| 78 |
+
|
| 79 |
+
See the [mlx-vlm sapiens2 port](https://github.com/Blaizzy/mlx-vlm/tree/main/mlx_vlm/models/sapiens2) for implementation details.
|
| 80 |
+
|
| 81 |
+
## License
|
| 82 |
+
|
| 83 |
+
Weights released under the [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md); this MLX repackaging inherits that license.
|
| 84 |
+
|
| 85 |
+
## Citation
|
| 86 |
+
|
| 87 |
+
```bibtex
|
| 88 |
+
@article{khirodkarsapiens2,
|
| 89 |
+
title = {Sapiens2},
|
| 90 |
+
author = {Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan
|
| 91 |
+
and Su, Zhaoen and Saito, Shunsuke},
|
| 92 |
+
journal= {arXiv preprint arXiv:2604.21681},
|
| 93 |
+
year = {2026}
|
| 94 |
+
}
|
| 95 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backbone_config": {
|
| 3 |
+
"model_type": "sapiens2_backbone",
|
| 4 |
+
"arch": "sapiens2_0.4b",
|
| 5 |
+
"embed_dims": 1024,
|
| 6 |
+
"num_layers": 24,
|
| 7 |
+
"num_heads": 16,
|
| 8 |
+
"feedforward_channels": 4096,
|
| 9 |
+
"image_size": [
|
| 10 |
+
1024,
|
| 11 |
+
768
|
| 12 |
+
],
|
| 13 |
+
"patch_size": 16,
|
| 14 |
+
"n_storage_tokens": 8,
|
| 15 |
+
"rope_base": 100.0,
|
| 16 |
+
"rope_normalize_coords": "separate",
|
| 17 |
+
"mhsa_early": 8,
|
| 18 |
+
"mhsa_late": 8,
|
| 19 |
+
"layer_scale_init_value": 0.0001,
|
| 20 |
+
"final_norm": true
|
| 21 |
+
},
|
| 22 |
+
"head_config": {
|
| 23 |
+
"model_type": "sapiens2_head",
|
| 24 |
+
"task": "seg",
|
| 25 |
+
"in_channels": 1024,
|
| 26 |
+
"deconv_out_channels": [
|
| 27 |
+
512,
|
| 28 |
+
256,
|
| 29 |
+
128,
|
| 30 |
+
64
|
| 31 |
+
],
|
| 32 |
+
"deconv_kernel_sizes": [
|
| 33 |
+
4,
|
| 34 |
+
4,
|
| 35 |
+
4,
|
| 36 |
+
4
|
| 37 |
+
],
|
| 38 |
+
"conv_out_channels": [
|
| 39 |
+
64,
|
| 40 |
+
64
|
| 41 |
+
],
|
| 42 |
+
"conv_kernel_sizes": [
|
| 43 |
+
1,
|
| 44 |
+
1
|
| 45 |
+
],
|
| 46 |
+
"num_keypoints": 308,
|
| 47 |
+
"num_classes": 29,
|
| 48 |
+
"upsample_channels": null,
|
| 49 |
+
"scale_conv_out_channels": null,
|
| 50 |
+
"scale_conv_kernel_sizes": null,
|
| 51 |
+
"scale_final_layer": null
|
| 52 |
+
},
|
| 53 |
+
"model_type": "sapiens2",
|
| 54 |
+
"quantization": {
|
| 55 |
+
"group_size": 64,
|
| 56 |
+
"bits": 5,
|
| 57 |
+
"mode": "affine"
|
| 58 |
+
},
|
| 59 |
+
"quantization_config": {
|
| 60 |
+
"group_size": 64,
|
| 61 |
+
"bits": 5,
|
| 62 |
+
"mode": "affine"
|
| 63 |
+
},
|
| 64 |
+
"size": "0.4b",
|
| 65 |
+
"task": "seg",
|
| 66 |
+
"vision_config": {}
|
| 67 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cdfca9b87513dd9421107d347192966c54a3f8417f405b674ba6074d6e94ed3
|
| 3 |
+
size 345121587
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 345046964
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"backbone.blocks.0.attn.gamma.weight": "model.safetensors",
|
| 7 |
+
"backbone.blocks.0.attn.k_norm.weight": "model.safetensors",
|
| 8 |
+
"backbone.blocks.0.attn.proj.bias": "model.safetensors",
|
| 9 |
+
"backbone.blocks.0.attn.proj.biases": "model.safetensors",
|
| 10 |
+
"backbone.blocks.0.attn.proj.scales": "model.safetensors",
|
| 11 |
+
"backbone.blocks.0.attn.proj.weight": "model.safetensors",
|
| 12 |
+
"backbone.blocks.0.attn.q_norm.weight": "model.safetensors",
|
| 13 |
+
"backbone.blocks.0.attn.wk.bias": "model.safetensors",
|
| 14 |
+
"backbone.blocks.0.attn.wk.biases": "model.safetensors",
|
| 15 |
+
"backbone.blocks.0.attn.wk.scales": "model.safetensors",
|
| 16 |
+
"backbone.blocks.0.attn.wk.weight": "model.safetensors",
|
| 17 |
+
"backbone.blocks.0.attn.wq.bias": "model.safetensors",
|
| 18 |
+
"backbone.blocks.0.attn.wq.biases": "model.safetensors",
|
| 19 |
+
"backbone.blocks.0.attn.wq.scales": "model.safetensors",
|
| 20 |
+
"backbone.blocks.0.attn.wq.weight": "model.safetensors",
|
| 21 |
+
"backbone.blocks.0.attn.wv.bias": "model.safetensors",
|
| 22 |
+
"backbone.blocks.0.attn.wv.biases": "model.safetensors",
|
| 23 |
+
"backbone.blocks.0.attn.wv.scales": "model.safetensors",
|
| 24 |
+
"backbone.blocks.0.attn.wv.weight": "model.safetensors",
|
| 25 |
+
"backbone.blocks.0.ffn.w12.bias": "model.safetensors",
|
| 26 |
+
"backbone.blocks.0.ffn.w12.biases": "model.safetensors",
|
| 27 |
+
"backbone.blocks.0.ffn.w12.scales": "model.safetensors",
|
| 28 |
+
"backbone.blocks.0.ffn.w12.weight": "model.safetensors",
|
| 29 |
+
"backbone.blocks.0.ffn.w3.bias": "model.safetensors",
|
| 30 |
+
"backbone.blocks.0.ffn.w3.biases": "model.safetensors",
|
| 31 |
+
"backbone.blocks.0.ffn.w3.scales": "model.safetensors",
|
| 32 |
+
"backbone.blocks.0.ffn.w3.weight": "model.safetensors",
|
| 33 |
+
"backbone.blocks.0.ln1.weight": "model.safetensors",
|
| 34 |
+
"backbone.blocks.0.ln2.weight": "model.safetensors",
|
| 35 |
+
"backbone.blocks.1.attn.gamma.weight": "model.safetensors",
|
| 36 |
+
"backbone.blocks.1.attn.k_norm.weight": "model.safetensors",
|
| 37 |
+
"backbone.blocks.1.attn.proj.bias": "model.safetensors",
|
| 38 |
+
"backbone.blocks.1.attn.proj.biases": "model.safetensors",
|
| 39 |
+
"backbone.blocks.1.attn.proj.scales": "model.safetensors",
|
| 40 |
+
"backbone.blocks.1.attn.proj.weight": "model.safetensors",
|
| 41 |
+
"backbone.blocks.1.attn.q_norm.weight": "model.safetensors",
|
| 42 |
+
"backbone.blocks.1.attn.wk.bias": "model.safetensors",
|
| 43 |
+
"backbone.blocks.1.attn.wk.biases": "model.safetensors",
|
| 44 |
+
"backbone.blocks.1.attn.wk.scales": "model.safetensors",
|
| 45 |
+
"backbone.blocks.1.attn.wk.weight": "model.safetensors",
|
| 46 |
+
"backbone.blocks.1.attn.wq.bias": "model.safetensors",
|
| 47 |
+
"backbone.blocks.1.attn.wq.biases": "model.safetensors",
|
| 48 |
+
"backbone.blocks.1.attn.wq.scales": "model.safetensors",
|
| 49 |
+
"backbone.blocks.1.attn.wq.weight": "model.safetensors",
|
| 50 |
+
"backbone.blocks.1.attn.wv.bias": "model.safetensors",
|
| 51 |
+
"backbone.blocks.1.attn.wv.biases": "model.safetensors",
|
| 52 |
+
"backbone.blocks.1.attn.wv.scales": "model.safetensors",
|
| 53 |
+
"backbone.blocks.1.attn.wv.weight": "model.safetensors",
|
| 54 |
+
"backbone.blocks.1.ffn.w12.bias": "model.safetensors",
|
| 55 |
+
"backbone.blocks.1.ffn.w12.biases": "model.safetensors",
|
| 56 |
+
"backbone.blocks.1.ffn.w12.scales": "model.safetensors",
|
| 57 |
+
"backbone.blocks.1.ffn.w12.weight": "model.safetensors",
|
| 58 |
+
"backbone.blocks.1.ffn.w3.bias": "model.safetensors",
|
| 59 |
+
"backbone.blocks.1.ffn.w3.biases": "model.safetensors",
|
| 60 |
+
"backbone.blocks.1.ffn.w3.scales": "model.safetensors",
|
| 61 |
+
"backbone.blocks.1.ffn.w3.weight": "model.safetensors",
|
| 62 |
+
"backbone.blocks.1.ln1.weight": "model.safetensors",
|
| 63 |
+
"backbone.blocks.1.ln2.weight": "model.safetensors",
|
| 64 |
+
"backbone.blocks.10.attn.gamma.weight": "model.safetensors",
|
| 65 |
+
"backbone.blocks.10.attn.k_norm.weight": "model.safetensors",
|
| 66 |
+
"backbone.blocks.10.attn.proj.bias": "model.safetensors",
|
| 67 |
+
"backbone.blocks.10.attn.proj.biases": "model.safetensors",
|
| 68 |
+
"backbone.blocks.10.attn.proj.scales": "model.safetensors",
|
| 69 |
+
"backbone.blocks.10.attn.proj.weight": "model.safetensors",
|
| 70 |
+
"backbone.blocks.10.attn.q_norm.weight": "model.safetensors",
|
| 71 |
+
"backbone.blocks.10.attn.wk.bias": "model.safetensors",
|
| 72 |
+
"backbone.blocks.10.attn.wk.biases": "model.safetensors",
|
| 73 |
+
"backbone.blocks.10.attn.wk.scales": "model.safetensors",
|
| 74 |
+
"backbone.blocks.10.attn.wk.weight": "model.safetensors",
|
| 75 |
+
"backbone.blocks.10.attn.wq.bias": "model.safetensors",
|
| 76 |
+
"backbone.blocks.10.attn.wq.biases": "model.safetensors",
|
| 77 |
+
"backbone.blocks.10.attn.wq.scales": "model.safetensors",
|
| 78 |
+
"backbone.blocks.10.attn.wq.weight": "model.safetensors",
|
| 79 |
+
"backbone.blocks.10.attn.wv.bias": "model.safetensors",
|
| 80 |
+
"backbone.blocks.10.attn.wv.biases": "model.safetensors",
|
| 81 |
+
"backbone.blocks.10.attn.wv.scales": "model.safetensors",
|
| 82 |
+
"backbone.blocks.10.attn.wv.weight": "model.safetensors",
|
| 83 |
+
"backbone.blocks.10.ffn.w12.bias": "model.safetensors",
|
| 84 |
+
"backbone.blocks.10.ffn.w12.biases": "model.safetensors",
|
| 85 |
+
"backbone.blocks.10.ffn.w12.scales": "model.safetensors",
|
| 86 |
+
"backbone.blocks.10.ffn.w12.weight": "model.safetensors",
|
| 87 |
+
"backbone.blocks.10.ffn.w3.bias": "model.safetensors",
|
| 88 |
+
"backbone.blocks.10.ffn.w3.biases": "model.safetensors",
|
| 89 |
+
"backbone.blocks.10.ffn.w3.scales": "model.safetensors",
|
| 90 |
+
"backbone.blocks.10.ffn.w3.weight": "model.safetensors",
|
| 91 |
+
"backbone.blocks.10.ln1.weight": "model.safetensors",
|
| 92 |
+
"backbone.blocks.10.ln2.weight": "model.safetensors",
|
| 93 |
+
"backbone.blocks.11.attn.gamma.weight": "model.safetensors",
|
| 94 |
+
"backbone.blocks.11.attn.k_norm.weight": "model.safetensors",
|
| 95 |
+
"backbone.blocks.11.attn.proj.bias": "model.safetensors",
|
| 96 |
+
"backbone.blocks.11.attn.proj.biases": "model.safetensors",
|
| 97 |
+
"backbone.blocks.11.attn.proj.scales": "model.safetensors",
|
| 98 |
+
"backbone.blocks.11.attn.proj.weight": "model.safetensors",
|
| 99 |
+
"backbone.blocks.11.attn.q_norm.weight": "model.safetensors",
|
| 100 |
+
"backbone.blocks.11.attn.wk.bias": "model.safetensors",
|
| 101 |
+
"backbone.blocks.11.attn.wk.biases": "model.safetensors",
|
| 102 |
+
"backbone.blocks.11.attn.wk.scales": "model.safetensors",
|
| 103 |
+
"backbone.blocks.11.attn.wk.weight": "model.safetensors",
|
| 104 |
+
"backbone.blocks.11.attn.wq.bias": "model.safetensors",
|
| 105 |
+
"backbone.blocks.11.attn.wq.biases": "model.safetensors",
|
| 106 |
+
"backbone.blocks.11.attn.wq.scales": "model.safetensors",
|
| 107 |
+
"backbone.blocks.11.attn.wq.weight": "model.safetensors",
|
| 108 |
+
"backbone.blocks.11.attn.wv.bias": "model.safetensors",
|
| 109 |
+
"backbone.blocks.11.attn.wv.biases": "model.safetensors",
|
| 110 |
+
"backbone.blocks.11.attn.wv.scales": "model.safetensors",
|
| 111 |
+
"backbone.blocks.11.attn.wv.weight": "model.safetensors",
|
| 112 |
+
"backbone.blocks.11.ffn.w12.bias": "model.safetensors",
|
| 113 |
+
"backbone.blocks.11.ffn.w12.biases": "model.safetensors",
|
| 114 |
+
"backbone.blocks.11.ffn.w12.scales": "model.safetensors",
|
| 115 |
+
"backbone.blocks.11.ffn.w12.weight": "model.safetensors",
|
| 116 |
+
"backbone.blocks.11.ffn.w3.bias": "model.safetensors",
|
| 117 |
+
"backbone.blocks.11.ffn.w3.biases": "model.safetensors",
|
| 118 |
+
"backbone.blocks.11.ffn.w3.scales": "model.safetensors",
|
| 119 |
+
"backbone.blocks.11.ffn.w3.weight": "model.safetensors",
|
| 120 |
+
"backbone.blocks.11.ln1.weight": "model.safetensors",
|
| 121 |
+
"backbone.blocks.11.ln2.weight": "model.safetensors",
|
| 122 |
+
"backbone.blocks.12.attn.gamma.weight": "model.safetensors",
|
| 123 |
+
"backbone.blocks.12.attn.k_norm.weight": "model.safetensors",
|
| 124 |
+
"backbone.blocks.12.attn.proj.bias": "model.safetensors",
|
| 125 |
+
"backbone.blocks.12.attn.proj.biases": "model.safetensors",
|
| 126 |
+
"backbone.blocks.12.attn.proj.scales": "model.safetensors",
|
| 127 |
+
"backbone.blocks.12.attn.proj.weight": "model.safetensors",
|
| 128 |
+
"backbone.blocks.12.attn.q_norm.weight": "model.safetensors",
|
| 129 |
+
"backbone.blocks.12.attn.wk.bias": "model.safetensors",
|
| 130 |
+
"backbone.blocks.12.attn.wk.biases": "model.safetensors",
|
| 131 |
+
"backbone.blocks.12.attn.wk.scales": "model.safetensors",
|
| 132 |
+
"backbone.blocks.12.attn.wk.weight": "model.safetensors",
|
| 133 |
+
"backbone.blocks.12.attn.wq.bias": "model.safetensors",
|
| 134 |
+
"backbone.blocks.12.attn.wq.biases": "model.safetensors",
|
| 135 |
+
"backbone.blocks.12.attn.wq.scales": "model.safetensors",
|
| 136 |
+
"backbone.blocks.12.attn.wq.weight": "model.safetensors",
|
| 137 |
+
"backbone.blocks.12.attn.wv.bias": "model.safetensors",
|
| 138 |
+
"backbone.blocks.12.attn.wv.biases": "model.safetensors",
|
| 139 |
+
"backbone.blocks.12.attn.wv.scales": "model.safetensors",
|
| 140 |
+
"backbone.blocks.12.attn.wv.weight": "model.safetensors",
|
| 141 |
+
"backbone.blocks.12.ffn.w12.bias": "model.safetensors",
|
| 142 |
+
"backbone.blocks.12.ffn.w12.biases": "model.safetensors",
|
| 143 |
+
"backbone.blocks.12.ffn.w12.scales": "model.safetensors",
|
| 144 |
+
"backbone.blocks.12.ffn.w12.weight": "model.safetensors",
|
| 145 |
+
"backbone.blocks.12.ffn.w3.bias": "model.safetensors",
|
| 146 |
+
"backbone.blocks.12.ffn.w3.biases": "model.safetensors",
|
| 147 |
+
"backbone.blocks.12.ffn.w3.scales": "model.safetensors",
|
| 148 |
+
"backbone.blocks.12.ffn.w3.weight": "model.safetensors",
|
| 149 |
+
"backbone.blocks.12.ln1.weight": "model.safetensors",
|
| 150 |
+
"backbone.blocks.12.ln2.weight": "model.safetensors",
|
| 151 |
+
"backbone.blocks.13.attn.gamma.weight": "model.safetensors",
|
| 152 |
+
"backbone.blocks.13.attn.k_norm.weight": "model.safetensors",
|
| 153 |
+
"backbone.blocks.13.attn.proj.bias": "model.safetensors",
|
| 154 |
+
"backbone.blocks.13.attn.proj.biases": "model.safetensors",
|
| 155 |
+
"backbone.blocks.13.attn.proj.scales": "model.safetensors",
|
| 156 |
+
"backbone.blocks.13.attn.proj.weight": "model.safetensors",
|
| 157 |
+
"backbone.blocks.13.attn.q_norm.weight": "model.safetensors",
|
| 158 |
+
"backbone.blocks.13.attn.wk.bias": "model.safetensors",
|
| 159 |
+
"backbone.blocks.13.attn.wk.biases": "model.safetensors",
|
| 160 |
+
"backbone.blocks.13.attn.wk.scales": "model.safetensors",
|
| 161 |
+
"backbone.blocks.13.attn.wk.weight": "model.safetensors",
|
| 162 |
+
"backbone.blocks.13.attn.wq.bias": "model.safetensors",
|
| 163 |
+
"backbone.blocks.13.attn.wq.biases": "model.safetensors",
|
| 164 |
+
"backbone.blocks.13.attn.wq.scales": "model.safetensors",
|
| 165 |
+
"backbone.blocks.13.attn.wq.weight": "model.safetensors",
|
| 166 |
+
"backbone.blocks.13.attn.wv.bias": "model.safetensors",
|
| 167 |
+
"backbone.blocks.13.attn.wv.biases": "model.safetensors",
|
| 168 |
+
"backbone.blocks.13.attn.wv.scales": "model.safetensors",
|
| 169 |
+
"backbone.blocks.13.attn.wv.weight": "model.safetensors",
|
| 170 |
+
"backbone.blocks.13.ffn.w12.bias": "model.safetensors",
|
| 171 |
+
"backbone.blocks.13.ffn.w12.biases": "model.safetensors",
|
| 172 |
+
"backbone.blocks.13.ffn.w12.scales": "model.safetensors",
|
| 173 |
+
"backbone.blocks.13.ffn.w12.weight": "model.safetensors",
|
| 174 |
+
"backbone.blocks.13.ffn.w3.bias": "model.safetensors",
|
| 175 |
+
"backbone.blocks.13.ffn.w3.biases": "model.safetensors",
|
| 176 |
+
"backbone.blocks.13.ffn.w3.scales": "model.safetensors",
|
| 177 |
+
"backbone.blocks.13.ffn.w3.weight": "model.safetensors",
|
| 178 |
+
"backbone.blocks.13.ln1.weight": "model.safetensors",
|
| 179 |
+
"backbone.blocks.13.ln2.weight": "model.safetensors",
|
| 180 |
+
"backbone.blocks.14.attn.gamma.weight": "model.safetensors",
|
| 181 |
+
"backbone.blocks.14.attn.k_norm.weight": "model.safetensors",
|
| 182 |
+
"backbone.blocks.14.attn.proj.bias": "model.safetensors",
|
| 183 |
+
"backbone.blocks.14.attn.proj.biases": "model.safetensors",
|
| 184 |
+
"backbone.blocks.14.attn.proj.scales": "model.safetensors",
|
| 185 |
+
"backbone.blocks.14.attn.proj.weight": "model.safetensors",
|
| 186 |
+
"backbone.blocks.14.attn.q_norm.weight": "model.safetensors",
|
| 187 |
+
"backbone.blocks.14.attn.wk.bias": "model.safetensors",
|
| 188 |
+
"backbone.blocks.14.attn.wk.biases": "model.safetensors",
|
| 189 |
+
"backbone.blocks.14.attn.wk.scales": "model.safetensors",
|
| 190 |
+
"backbone.blocks.14.attn.wk.weight": "model.safetensors",
|
| 191 |
+
"backbone.blocks.14.attn.wq.bias": "model.safetensors",
|
| 192 |
+
"backbone.blocks.14.attn.wq.biases": "model.safetensors",
|
| 193 |
+
"backbone.blocks.14.attn.wq.scales": "model.safetensors",
|
| 194 |
+
"backbone.blocks.14.attn.wq.weight": "model.safetensors",
|
| 195 |
+
"backbone.blocks.14.attn.wv.bias": "model.safetensors",
|
| 196 |
+
"backbone.blocks.14.attn.wv.biases": "model.safetensors",
|
| 197 |
+
"backbone.blocks.14.attn.wv.scales": "model.safetensors",
|
| 198 |
+
"backbone.blocks.14.attn.wv.weight": "model.safetensors",
|
| 199 |
+
"backbone.blocks.14.ffn.w12.bias": "model.safetensors",
|
| 200 |
+
"backbone.blocks.14.ffn.w12.biases": "model.safetensors",
|
| 201 |
+
"backbone.blocks.14.ffn.w12.scales": "model.safetensors",
|
| 202 |
+
"backbone.blocks.14.ffn.w12.weight": "model.safetensors",
|
| 203 |
+
"backbone.blocks.14.ffn.w3.bias": "model.safetensors",
|
| 204 |
+
"backbone.blocks.14.ffn.w3.biases": "model.safetensors",
|
| 205 |
+
"backbone.blocks.14.ffn.w3.scales": "model.safetensors",
|
| 206 |
+
"backbone.blocks.14.ffn.w3.weight": "model.safetensors",
|
| 207 |
+
"backbone.blocks.14.ln1.weight": "model.safetensors",
|
| 208 |
+
"backbone.blocks.14.ln2.weight": "model.safetensors",
|
| 209 |
+
"backbone.blocks.15.attn.gamma.weight": "model.safetensors",
|
| 210 |
+
"backbone.blocks.15.attn.k_norm.weight": "model.safetensors",
|
| 211 |
+
"backbone.blocks.15.attn.proj.bias": "model.safetensors",
|
| 212 |
+
"backbone.blocks.15.attn.proj.biases": "model.safetensors",
|
| 213 |
+
"backbone.blocks.15.attn.proj.scales": "model.safetensors",
|
| 214 |
+
"backbone.blocks.15.attn.proj.weight": "model.safetensors",
|
| 215 |
+
"backbone.blocks.15.attn.q_norm.weight": "model.safetensors",
|
| 216 |
+
"backbone.blocks.15.attn.wk.bias": "model.safetensors",
|
| 217 |
+
"backbone.blocks.15.attn.wk.biases": "model.safetensors",
|
| 218 |
+
"backbone.blocks.15.attn.wk.scales": "model.safetensors",
|
| 219 |
+
"backbone.blocks.15.attn.wk.weight": "model.safetensors",
|
| 220 |
+
"backbone.blocks.15.attn.wq.bias": "model.safetensors",
|
| 221 |
+
"backbone.blocks.15.attn.wq.biases": "model.safetensors",
|
| 222 |
+
"backbone.blocks.15.attn.wq.scales": "model.safetensors",
|
| 223 |
+
"backbone.blocks.15.attn.wq.weight": "model.safetensors",
|
| 224 |
+
"backbone.blocks.15.attn.wv.bias": "model.safetensors",
|
| 225 |
+
"backbone.blocks.15.attn.wv.biases": "model.safetensors",
|
| 226 |
+
"backbone.blocks.15.attn.wv.scales": "model.safetensors",
|
| 227 |
+
"backbone.blocks.15.attn.wv.weight": "model.safetensors",
|
| 228 |
+
"backbone.blocks.15.ffn.w12.bias": "model.safetensors",
|
| 229 |
+
"backbone.blocks.15.ffn.w12.biases": "model.safetensors",
|
| 230 |
+
"backbone.blocks.15.ffn.w12.scales": "model.safetensors",
|
| 231 |
+
"backbone.blocks.15.ffn.w12.weight": "model.safetensors",
|
| 232 |
+
"backbone.blocks.15.ffn.w3.bias": "model.safetensors",
|
| 233 |
+
"backbone.blocks.15.ffn.w3.biases": "model.safetensors",
|
| 234 |
+
"backbone.blocks.15.ffn.w3.scales": "model.safetensors",
|
| 235 |
+
"backbone.blocks.15.ffn.w3.weight": "model.safetensors",
|
| 236 |
+
"backbone.blocks.15.ln1.weight": "model.safetensors",
|
| 237 |
+
"backbone.blocks.15.ln2.weight": "model.safetensors",
|
| 238 |
+
"backbone.blocks.16.attn.gamma.weight": "model.safetensors",
|
| 239 |
+
"backbone.blocks.16.attn.k_norm.weight": "model.safetensors",
|
| 240 |
+
"backbone.blocks.16.attn.proj.bias": "model.safetensors",
|
| 241 |
+
"backbone.blocks.16.attn.proj.biases": "model.safetensors",
|
| 242 |
+
"backbone.blocks.16.attn.proj.scales": "model.safetensors",
|
| 243 |
+
"backbone.blocks.16.attn.proj.weight": "model.safetensors",
|
| 244 |
+
"backbone.blocks.16.attn.q_norm.weight": "model.safetensors",
|
| 245 |
+
"backbone.blocks.16.attn.wk.bias": "model.safetensors",
|
| 246 |
+
"backbone.blocks.16.attn.wk.biases": "model.safetensors",
|
| 247 |
+
"backbone.blocks.16.attn.wk.scales": "model.safetensors",
|
| 248 |
+
"backbone.blocks.16.attn.wk.weight": "model.safetensors",
|
| 249 |
+
"backbone.blocks.16.attn.wq.bias": "model.safetensors",
|
| 250 |
+
"backbone.blocks.16.attn.wq.biases": "model.safetensors",
|
| 251 |
+
"backbone.blocks.16.attn.wq.scales": "model.safetensors",
|
| 252 |
+
"backbone.blocks.16.attn.wq.weight": "model.safetensors",
|
| 253 |
+
"backbone.blocks.16.attn.wv.bias": "model.safetensors",
|
| 254 |
+
"backbone.blocks.16.attn.wv.biases": "model.safetensors",
|
| 255 |
+
"backbone.blocks.16.attn.wv.scales": "model.safetensors",
|
| 256 |
+
"backbone.blocks.16.attn.wv.weight": "model.safetensors",
|
| 257 |
+
"backbone.blocks.16.ffn.w12.bias": "model.safetensors",
|
| 258 |
+
"backbone.blocks.16.ffn.w12.biases": "model.safetensors",
|
| 259 |
+
"backbone.blocks.16.ffn.w12.scales": "model.safetensors",
|
| 260 |
+
"backbone.blocks.16.ffn.w12.weight": "model.safetensors",
|
| 261 |
+
"backbone.blocks.16.ffn.w3.bias": "model.safetensors",
|
| 262 |
+
"backbone.blocks.16.ffn.w3.biases": "model.safetensors",
|
| 263 |
+
"backbone.blocks.16.ffn.w3.scales": "model.safetensors",
|
| 264 |
+
"backbone.blocks.16.ffn.w3.weight": "model.safetensors",
|
| 265 |
+
"backbone.blocks.16.ln1.weight": "model.safetensors",
|
| 266 |
+
"backbone.blocks.16.ln2.weight": "model.safetensors",
|
| 267 |
+
"backbone.blocks.17.attn.gamma.weight": "model.safetensors",
|
| 268 |
+
"backbone.blocks.17.attn.k_norm.weight": "model.safetensors",
|
| 269 |
+
"backbone.blocks.17.attn.proj.bias": "model.safetensors",
|
| 270 |
+
"backbone.blocks.17.attn.proj.biases": "model.safetensors",
|
| 271 |
+
"backbone.blocks.17.attn.proj.scales": "model.safetensors",
|
| 272 |
+
"backbone.blocks.17.attn.proj.weight": "model.safetensors",
|
| 273 |
+
"backbone.blocks.17.attn.q_norm.weight": "model.safetensors",
|
| 274 |
+
"backbone.blocks.17.attn.wk.bias": "model.safetensors",
|
| 275 |
+
"backbone.blocks.17.attn.wk.biases": "model.safetensors",
|
| 276 |
+
"backbone.blocks.17.attn.wk.scales": "model.safetensors",
|
| 277 |
+
"backbone.blocks.17.attn.wk.weight": "model.safetensors",
|
| 278 |
+
"backbone.blocks.17.attn.wq.bias": "model.safetensors",
|
| 279 |
+
"backbone.blocks.17.attn.wq.biases": "model.safetensors",
|
| 280 |
+
"backbone.blocks.17.attn.wq.scales": "model.safetensors",
|
| 281 |
+
"backbone.blocks.17.attn.wq.weight": "model.safetensors",
|
| 282 |
+
"backbone.blocks.17.attn.wv.bias": "model.safetensors",
|
| 283 |
+
"backbone.blocks.17.attn.wv.biases": "model.safetensors",
|
| 284 |
+
"backbone.blocks.17.attn.wv.scales": "model.safetensors",
|
| 285 |
+
"backbone.blocks.17.attn.wv.weight": "model.safetensors",
|
| 286 |
+
"backbone.blocks.17.ffn.w12.bias": "model.safetensors",
|
| 287 |
+
"backbone.blocks.17.ffn.w12.biases": "model.safetensors",
|
| 288 |
+
"backbone.blocks.17.ffn.w12.scales": "model.safetensors",
|
| 289 |
+
"backbone.blocks.17.ffn.w12.weight": "model.safetensors",
|
| 290 |
+
"backbone.blocks.17.ffn.w3.bias": "model.safetensors",
|
| 291 |
+
"backbone.blocks.17.ffn.w3.biases": "model.safetensors",
|
| 292 |
+
"backbone.blocks.17.ffn.w3.scales": "model.safetensors",
|
| 293 |
+
"backbone.blocks.17.ffn.w3.weight": "model.safetensors",
|
| 294 |
+
"backbone.blocks.17.ln1.weight": "model.safetensors",
|
| 295 |
+
"backbone.blocks.17.ln2.weight": "model.safetensors",
|
| 296 |
+
"backbone.blocks.18.attn.gamma.weight": "model.safetensors",
|
| 297 |
+
"backbone.blocks.18.attn.k_norm.weight": "model.safetensors",
|
| 298 |
+
"backbone.blocks.18.attn.proj.bias": "model.safetensors",
|
| 299 |
+
"backbone.blocks.18.attn.proj.biases": "model.safetensors",
|
| 300 |
+
"backbone.blocks.18.attn.proj.scales": "model.safetensors",
|
| 301 |
+
"backbone.blocks.18.attn.proj.weight": "model.safetensors",
|
| 302 |
+
"backbone.blocks.18.attn.q_norm.weight": "model.safetensors",
|
| 303 |
+
"backbone.blocks.18.attn.wk.bias": "model.safetensors",
|
| 304 |
+
"backbone.blocks.18.attn.wk.biases": "model.safetensors",
|
| 305 |
+
"backbone.blocks.18.attn.wk.scales": "model.safetensors",
|
| 306 |
+
"backbone.blocks.18.attn.wk.weight": "model.safetensors",
|
| 307 |
+
"backbone.blocks.18.attn.wq.bias": "model.safetensors",
|
| 308 |
+
"backbone.blocks.18.attn.wq.biases": "model.safetensors",
|
| 309 |
+
"backbone.blocks.18.attn.wq.scales": "model.safetensors",
|
| 310 |
+
"backbone.blocks.18.attn.wq.weight": "model.safetensors",
|
| 311 |
+
"backbone.blocks.18.attn.wv.bias": "model.safetensors",
|
| 312 |
+
"backbone.blocks.18.attn.wv.biases": "model.safetensors",
|
| 313 |
+
"backbone.blocks.18.attn.wv.scales": "model.safetensors",
|
| 314 |
+
"backbone.blocks.18.attn.wv.weight": "model.safetensors",
|
| 315 |
+
"backbone.blocks.18.ffn.w12.bias": "model.safetensors",
|
| 316 |
+
"backbone.blocks.18.ffn.w12.biases": "model.safetensors",
|
| 317 |
+
"backbone.blocks.18.ffn.w12.scales": "model.safetensors",
|
| 318 |
+
"backbone.blocks.18.ffn.w12.weight": "model.safetensors",
|
| 319 |
+
"backbone.blocks.18.ffn.w3.bias": "model.safetensors",
|
| 320 |
+
"backbone.blocks.18.ffn.w3.biases": "model.safetensors",
|
| 321 |
+
"backbone.blocks.18.ffn.w3.scales": "model.safetensors",
|
| 322 |
+
"backbone.blocks.18.ffn.w3.weight": "model.safetensors",
|
| 323 |
+
"backbone.blocks.18.ln1.weight": "model.safetensors",
|
| 324 |
+
"backbone.blocks.18.ln2.weight": "model.safetensors",
|
| 325 |
+
"backbone.blocks.19.attn.gamma.weight": "model.safetensors",
|
| 326 |
+
"backbone.blocks.19.attn.k_norm.weight": "model.safetensors",
|
| 327 |
+
"backbone.blocks.19.attn.proj.bias": "model.safetensors",
|
| 328 |
+
"backbone.blocks.19.attn.proj.biases": "model.safetensors",
|
| 329 |
+
"backbone.blocks.19.attn.proj.scales": "model.safetensors",
|
| 330 |
+
"backbone.blocks.19.attn.proj.weight": "model.safetensors",
|
| 331 |
+
"backbone.blocks.19.attn.q_norm.weight": "model.safetensors",
|
| 332 |
+
"backbone.blocks.19.attn.wk.bias": "model.safetensors",
|
| 333 |
+
"backbone.blocks.19.attn.wk.biases": "model.safetensors",
|
| 334 |
+
"backbone.blocks.19.attn.wk.scales": "model.safetensors",
|
| 335 |
+
"backbone.blocks.19.attn.wk.weight": "model.safetensors",
|
| 336 |
+
"backbone.blocks.19.attn.wq.bias": "model.safetensors",
|
| 337 |
+
"backbone.blocks.19.attn.wq.biases": "model.safetensors",
|
| 338 |
+
"backbone.blocks.19.attn.wq.scales": "model.safetensors",
|
| 339 |
+
"backbone.blocks.19.attn.wq.weight": "model.safetensors",
|
| 340 |
+
"backbone.blocks.19.attn.wv.bias": "model.safetensors",
|
| 341 |
+
"backbone.blocks.19.attn.wv.biases": "model.safetensors",
|
| 342 |
+
"backbone.blocks.19.attn.wv.scales": "model.safetensors",
|
| 343 |
+
"backbone.blocks.19.attn.wv.weight": "model.safetensors",
|
| 344 |
+
"backbone.blocks.19.ffn.w12.bias": "model.safetensors",
|
| 345 |
+
"backbone.blocks.19.ffn.w12.biases": "model.safetensors",
|
| 346 |
+
"backbone.blocks.19.ffn.w12.scales": "model.safetensors",
|
| 347 |
+
"backbone.blocks.19.ffn.w12.weight": "model.safetensors",
|
| 348 |
+
"backbone.blocks.19.ffn.w3.bias": "model.safetensors",
|
| 349 |
+
"backbone.blocks.19.ffn.w3.biases": "model.safetensors",
|
| 350 |
+
"backbone.blocks.19.ffn.w3.scales": "model.safetensors",
|
| 351 |
+
"backbone.blocks.19.ffn.w3.weight": "model.safetensors",
|
| 352 |
+
"backbone.blocks.19.ln1.weight": "model.safetensors",
|
| 353 |
+
"backbone.blocks.19.ln2.weight": "model.safetensors",
|
| 354 |
+
"backbone.blocks.2.attn.gamma.weight": "model.safetensors",
|
| 355 |
+
"backbone.blocks.2.attn.k_norm.weight": "model.safetensors",
|
| 356 |
+
"backbone.blocks.2.attn.proj.bias": "model.safetensors",
|
| 357 |
+
"backbone.blocks.2.attn.proj.biases": "model.safetensors",
|
| 358 |
+
"backbone.blocks.2.attn.proj.scales": "model.safetensors",
|
| 359 |
+
"backbone.blocks.2.attn.proj.weight": "model.safetensors",
|
| 360 |
+
"backbone.blocks.2.attn.q_norm.weight": "model.safetensors",
|
| 361 |
+
"backbone.blocks.2.attn.wk.bias": "model.safetensors",
|
| 362 |
+
"backbone.blocks.2.attn.wk.biases": "model.safetensors",
|
| 363 |
+
"backbone.blocks.2.attn.wk.scales": "model.safetensors",
|
| 364 |
+
"backbone.blocks.2.attn.wk.weight": "model.safetensors",
|
| 365 |
+
"backbone.blocks.2.attn.wq.bias": "model.safetensors",
|
| 366 |
+
"backbone.blocks.2.attn.wq.biases": "model.safetensors",
|
| 367 |
+
"backbone.blocks.2.attn.wq.scales": "model.safetensors",
|
| 368 |
+
"backbone.blocks.2.attn.wq.weight": "model.safetensors",
|
| 369 |
+
"backbone.blocks.2.attn.wv.bias": "model.safetensors",
|
| 370 |
+
"backbone.blocks.2.attn.wv.biases": "model.safetensors",
|
| 371 |
+
"backbone.blocks.2.attn.wv.scales": "model.safetensors",
|
| 372 |
+
"backbone.blocks.2.attn.wv.weight": "model.safetensors",
|
| 373 |
+
"backbone.blocks.2.ffn.w12.bias": "model.safetensors",
|
| 374 |
+
"backbone.blocks.2.ffn.w12.biases": "model.safetensors",
|
| 375 |
+
"backbone.blocks.2.ffn.w12.scales": "model.safetensors",
|
| 376 |
+
"backbone.blocks.2.ffn.w12.weight": "model.safetensors",
|
| 377 |
+
"backbone.blocks.2.ffn.w3.bias": "model.safetensors",
|
| 378 |
+
"backbone.blocks.2.ffn.w3.biases": "model.safetensors",
|
| 379 |
+
"backbone.blocks.2.ffn.w3.scales": "model.safetensors",
|
| 380 |
+
"backbone.blocks.2.ffn.w3.weight": "model.safetensors",
|
| 381 |
+
"backbone.blocks.2.ln1.weight": "model.safetensors",
|
| 382 |
+
"backbone.blocks.2.ln2.weight": "model.safetensors",
|
| 383 |
+
"backbone.blocks.20.attn.gamma.weight": "model.safetensors",
|
| 384 |
+
"backbone.blocks.20.attn.k_norm.weight": "model.safetensors",
|
| 385 |
+
"backbone.blocks.20.attn.proj.bias": "model.safetensors",
|
| 386 |
+
"backbone.blocks.20.attn.proj.biases": "model.safetensors",
|
| 387 |
+
"backbone.blocks.20.attn.proj.scales": "model.safetensors",
|
| 388 |
+
"backbone.blocks.20.attn.proj.weight": "model.safetensors",
|
| 389 |
+
"backbone.blocks.20.attn.q_norm.weight": "model.safetensors",
|
| 390 |
+
"backbone.blocks.20.attn.wk.bias": "model.safetensors",
|
| 391 |
+
"backbone.blocks.20.attn.wk.biases": "model.safetensors",
|
| 392 |
+
"backbone.blocks.20.attn.wk.scales": "model.safetensors",
|
| 393 |
+
"backbone.blocks.20.attn.wk.weight": "model.safetensors",
|
| 394 |
+
"backbone.blocks.20.attn.wq.bias": "model.safetensors",
|
| 395 |
+
"backbone.blocks.20.attn.wq.biases": "model.safetensors",
|
| 396 |
+
"backbone.blocks.20.attn.wq.scales": "model.safetensors",
|
| 397 |
+
"backbone.blocks.20.attn.wq.weight": "model.safetensors",
|
| 398 |
+
"backbone.blocks.20.attn.wv.bias": "model.safetensors",
|
| 399 |
+
"backbone.blocks.20.attn.wv.biases": "model.safetensors",
|
| 400 |
+
"backbone.blocks.20.attn.wv.scales": "model.safetensors",
|
| 401 |
+
"backbone.blocks.20.attn.wv.weight": "model.safetensors",
|
| 402 |
+
"backbone.blocks.20.ffn.w12.bias": "model.safetensors",
|
| 403 |
+
"backbone.blocks.20.ffn.w12.biases": "model.safetensors",
|
| 404 |
+
"backbone.blocks.20.ffn.w12.scales": "model.safetensors",
|
| 405 |
+
"backbone.blocks.20.ffn.w12.weight": "model.safetensors",
|
| 406 |
+
"backbone.blocks.20.ffn.w3.bias": "model.safetensors",
|
| 407 |
+
"backbone.blocks.20.ffn.w3.biases": "model.safetensors",
|
| 408 |
+
"backbone.blocks.20.ffn.w3.scales": "model.safetensors",
|
| 409 |
+
"backbone.blocks.20.ffn.w3.weight": "model.safetensors",
|
| 410 |
+
"backbone.blocks.20.ln1.weight": "model.safetensors",
|
| 411 |
+
"backbone.blocks.20.ln2.weight": "model.safetensors",
|
| 412 |
+
"backbone.blocks.21.attn.gamma.weight": "model.safetensors",
|
| 413 |
+
"backbone.blocks.21.attn.k_norm.weight": "model.safetensors",
|
| 414 |
+
"backbone.blocks.21.attn.proj.bias": "model.safetensors",
|
| 415 |
+
"backbone.blocks.21.attn.proj.biases": "model.safetensors",
|
| 416 |
+
"backbone.blocks.21.attn.proj.scales": "model.safetensors",
|
| 417 |
+
"backbone.blocks.21.attn.proj.weight": "model.safetensors",
|
| 418 |
+
"backbone.blocks.21.attn.q_norm.weight": "model.safetensors",
|
| 419 |
+
"backbone.blocks.21.attn.wk.bias": "model.safetensors",
|
| 420 |
+
"backbone.blocks.21.attn.wk.biases": "model.safetensors",
|
| 421 |
+
"backbone.blocks.21.attn.wk.scales": "model.safetensors",
|
| 422 |
+
"backbone.blocks.21.attn.wk.weight": "model.safetensors",
|
| 423 |
+
"backbone.blocks.21.attn.wq.bias": "model.safetensors",
|
| 424 |
+
"backbone.blocks.21.attn.wq.biases": "model.safetensors",
|
| 425 |
+
"backbone.blocks.21.attn.wq.scales": "model.safetensors",
|
| 426 |
+
"backbone.blocks.21.attn.wq.weight": "model.safetensors",
|
| 427 |
+
"backbone.blocks.21.attn.wv.bias": "model.safetensors",
|
| 428 |
+
"backbone.blocks.21.attn.wv.biases": "model.safetensors",
|
| 429 |
+
"backbone.blocks.21.attn.wv.scales": "model.safetensors",
|
| 430 |
+
"backbone.blocks.21.attn.wv.weight": "model.safetensors",
|
| 431 |
+
"backbone.blocks.21.ffn.w12.bias": "model.safetensors",
|
| 432 |
+
"backbone.blocks.21.ffn.w12.biases": "model.safetensors",
|
| 433 |
+
"backbone.blocks.21.ffn.w12.scales": "model.safetensors",
|
| 434 |
+
"backbone.blocks.21.ffn.w12.weight": "model.safetensors",
|
| 435 |
+
"backbone.blocks.21.ffn.w3.bias": "model.safetensors",
|
| 436 |
+
"backbone.blocks.21.ffn.w3.biases": "model.safetensors",
|
| 437 |
+
"backbone.blocks.21.ffn.w3.scales": "model.safetensors",
|
| 438 |
+
"backbone.blocks.21.ffn.w3.weight": "model.safetensors",
|
| 439 |
+
"backbone.blocks.21.ln1.weight": "model.safetensors",
|
| 440 |
+
"backbone.blocks.21.ln2.weight": "model.safetensors",
|
| 441 |
+
"backbone.blocks.22.attn.gamma.weight": "model.safetensors",
|
| 442 |
+
"backbone.blocks.22.attn.k_norm.weight": "model.safetensors",
|
| 443 |
+
"backbone.blocks.22.attn.proj.bias": "model.safetensors",
|
| 444 |
+
"backbone.blocks.22.attn.proj.biases": "model.safetensors",
|
| 445 |
+
"backbone.blocks.22.attn.proj.scales": "model.safetensors",
|
| 446 |
+
"backbone.blocks.22.attn.proj.weight": "model.safetensors",
|
| 447 |
+
"backbone.blocks.22.attn.q_norm.weight": "model.safetensors",
|
| 448 |
+
"backbone.blocks.22.attn.wk.bias": "model.safetensors",
|
| 449 |
+
"backbone.blocks.22.attn.wk.biases": "model.safetensors",
|
| 450 |
+
"backbone.blocks.22.attn.wk.scales": "model.safetensors",
|
| 451 |
+
"backbone.blocks.22.attn.wk.weight": "model.safetensors",
|
| 452 |
+
"backbone.blocks.22.attn.wq.bias": "model.safetensors",
|
| 453 |
+
"backbone.blocks.22.attn.wq.biases": "model.safetensors",
|
| 454 |
+
"backbone.blocks.22.attn.wq.scales": "model.safetensors",
|
| 455 |
+
"backbone.blocks.22.attn.wq.weight": "model.safetensors",
|
| 456 |
+
"backbone.blocks.22.attn.wv.bias": "model.safetensors",
|
| 457 |
+
"backbone.blocks.22.attn.wv.biases": "model.safetensors",
|
| 458 |
+
"backbone.blocks.22.attn.wv.scales": "model.safetensors",
|
| 459 |
+
"backbone.blocks.22.attn.wv.weight": "model.safetensors",
|
| 460 |
+
"backbone.blocks.22.ffn.w12.bias": "model.safetensors",
|
| 461 |
+
"backbone.blocks.22.ffn.w12.biases": "model.safetensors",
|
| 462 |
+
"backbone.blocks.22.ffn.w12.scales": "model.safetensors",
|
| 463 |
+
"backbone.blocks.22.ffn.w12.weight": "model.safetensors",
|
| 464 |
+
"backbone.blocks.22.ffn.w3.bias": "model.safetensors",
|
| 465 |
+
"backbone.blocks.22.ffn.w3.biases": "model.safetensors",
|
| 466 |
+
"backbone.blocks.22.ffn.w3.scales": "model.safetensors",
|
| 467 |
+
"backbone.blocks.22.ffn.w3.weight": "model.safetensors",
|
| 468 |
+
"backbone.blocks.22.ln1.weight": "model.safetensors",
|
| 469 |
+
"backbone.blocks.22.ln2.weight": "model.safetensors",
|
| 470 |
+
"backbone.blocks.23.attn.gamma.weight": "model.safetensors",
|
| 471 |
+
"backbone.blocks.23.attn.k_norm.weight": "model.safetensors",
|
| 472 |
+
"backbone.blocks.23.attn.proj.bias": "model.safetensors",
|
| 473 |
+
"backbone.blocks.23.attn.proj.biases": "model.safetensors",
|
| 474 |
+
"backbone.blocks.23.attn.proj.scales": "model.safetensors",
|
| 475 |
+
"backbone.blocks.23.attn.proj.weight": "model.safetensors",
|
| 476 |
+
"backbone.blocks.23.attn.q_norm.weight": "model.safetensors",
|
| 477 |
+
"backbone.blocks.23.attn.wk.bias": "model.safetensors",
|
| 478 |
+
"backbone.blocks.23.attn.wk.biases": "model.safetensors",
|
| 479 |
+
"backbone.blocks.23.attn.wk.scales": "model.safetensors",
|
| 480 |
+
"backbone.blocks.23.attn.wk.weight": "model.safetensors",
|
| 481 |
+
"backbone.blocks.23.attn.wq.bias": "model.safetensors",
|
| 482 |
+
"backbone.blocks.23.attn.wq.biases": "model.safetensors",
|
| 483 |
+
"backbone.blocks.23.attn.wq.scales": "model.safetensors",
|
| 484 |
+
"backbone.blocks.23.attn.wq.weight": "model.safetensors",
|
| 485 |
+
"backbone.blocks.23.attn.wv.bias": "model.safetensors",
|
| 486 |
+
"backbone.blocks.23.attn.wv.biases": "model.safetensors",
|
| 487 |
+
"backbone.blocks.23.attn.wv.scales": "model.safetensors",
|
| 488 |
+
"backbone.blocks.23.attn.wv.weight": "model.safetensors",
|
| 489 |
+
"backbone.blocks.23.ffn.w12.bias": "model.safetensors",
|
| 490 |
+
"backbone.blocks.23.ffn.w12.biases": "model.safetensors",
|
| 491 |
+
"backbone.blocks.23.ffn.w12.scales": "model.safetensors",
|
| 492 |
+
"backbone.blocks.23.ffn.w12.weight": "model.safetensors",
|
| 493 |
+
"backbone.blocks.23.ffn.w3.bias": "model.safetensors",
|
| 494 |
+
"backbone.blocks.23.ffn.w3.biases": "model.safetensors",
|
| 495 |
+
"backbone.blocks.23.ffn.w3.scales": "model.safetensors",
|
| 496 |
+
"backbone.blocks.23.ffn.w3.weight": "model.safetensors",
|
| 497 |
+
"backbone.blocks.23.ln1.weight": "model.safetensors",
|
| 498 |
+
"backbone.blocks.23.ln2.weight": "model.safetensors",
|
| 499 |
+
"backbone.blocks.3.attn.gamma.weight": "model.safetensors",
|
| 500 |
+
"backbone.blocks.3.attn.k_norm.weight": "model.safetensors",
|
| 501 |
+
"backbone.blocks.3.attn.proj.bias": "model.safetensors",
|
| 502 |
+
"backbone.blocks.3.attn.proj.biases": "model.safetensors",
|
| 503 |
+
"backbone.blocks.3.attn.proj.scales": "model.safetensors",
|
| 504 |
+
"backbone.blocks.3.attn.proj.weight": "model.safetensors",
|
| 505 |
+
"backbone.blocks.3.attn.q_norm.weight": "model.safetensors",
|
| 506 |
+
"backbone.blocks.3.attn.wk.bias": "model.safetensors",
|
| 507 |
+
"backbone.blocks.3.attn.wk.biases": "model.safetensors",
|
| 508 |
+
"backbone.blocks.3.attn.wk.scales": "model.safetensors",
|
| 509 |
+
"backbone.blocks.3.attn.wk.weight": "model.safetensors",
|
| 510 |
+
"backbone.blocks.3.attn.wq.bias": "model.safetensors",
|
| 511 |
+
"backbone.blocks.3.attn.wq.biases": "model.safetensors",
|
| 512 |
+
"backbone.blocks.3.attn.wq.scales": "model.safetensors",
|
| 513 |
+
"backbone.blocks.3.attn.wq.weight": "model.safetensors",
|
| 514 |
+
"backbone.blocks.3.attn.wv.bias": "model.safetensors",
|
| 515 |
+
"backbone.blocks.3.attn.wv.biases": "model.safetensors",
|
| 516 |
+
"backbone.blocks.3.attn.wv.scales": "model.safetensors",
|
| 517 |
+
"backbone.blocks.3.attn.wv.weight": "model.safetensors",
|
| 518 |
+
"backbone.blocks.3.ffn.w12.bias": "model.safetensors",
|
| 519 |
+
"backbone.blocks.3.ffn.w12.biases": "model.safetensors",
|
| 520 |
+
"backbone.blocks.3.ffn.w12.scales": "model.safetensors",
|
| 521 |
+
"backbone.blocks.3.ffn.w12.weight": "model.safetensors",
|
| 522 |
+
"backbone.blocks.3.ffn.w3.bias": "model.safetensors",
|
| 523 |
+
"backbone.blocks.3.ffn.w3.biases": "model.safetensors",
|
| 524 |
+
"backbone.blocks.3.ffn.w3.scales": "model.safetensors",
|
| 525 |
+
"backbone.blocks.3.ffn.w3.weight": "model.safetensors",
|
| 526 |
+
"backbone.blocks.3.ln1.weight": "model.safetensors",
|
| 527 |
+
"backbone.blocks.3.ln2.weight": "model.safetensors",
|
| 528 |
+
"backbone.blocks.4.attn.gamma.weight": "model.safetensors",
|
| 529 |
+
"backbone.blocks.4.attn.k_norm.weight": "model.safetensors",
|
| 530 |
+
"backbone.blocks.4.attn.proj.bias": "model.safetensors",
|
| 531 |
+
"backbone.blocks.4.attn.proj.biases": "model.safetensors",
|
| 532 |
+
"backbone.blocks.4.attn.proj.scales": "model.safetensors",
|
| 533 |
+
"backbone.blocks.4.attn.proj.weight": "model.safetensors",
|
| 534 |
+
"backbone.blocks.4.attn.q_norm.weight": "model.safetensors",
|
| 535 |
+
"backbone.blocks.4.attn.wk.bias": "model.safetensors",
|
| 536 |
+
"backbone.blocks.4.attn.wk.biases": "model.safetensors",
|
| 537 |
+
"backbone.blocks.4.attn.wk.scales": "model.safetensors",
|
| 538 |
+
"backbone.blocks.4.attn.wk.weight": "model.safetensors",
|
| 539 |
+
"backbone.blocks.4.attn.wq.bias": "model.safetensors",
|
| 540 |
+
"backbone.blocks.4.attn.wq.biases": "model.safetensors",
|
| 541 |
+
"backbone.blocks.4.attn.wq.scales": "model.safetensors",
|
| 542 |
+
"backbone.blocks.4.attn.wq.weight": "model.safetensors",
|
| 543 |
+
"backbone.blocks.4.attn.wv.bias": "model.safetensors",
|
| 544 |
+
"backbone.blocks.4.attn.wv.biases": "model.safetensors",
|
| 545 |
+
"backbone.blocks.4.attn.wv.scales": "model.safetensors",
|
| 546 |
+
"backbone.blocks.4.attn.wv.weight": "model.safetensors",
|
| 547 |
+
"backbone.blocks.4.ffn.w12.bias": "model.safetensors",
|
| 548 |
+
"backbone.blocks.4.ffn.w12.biases": "model.safetensors",
|
| 549 |
+
"backbone.blocks.4.ffn.w12.scales": "model.safetensors",
|
| 550 |
+
"backbone.blocks.4.ffn.w12.weight": "model.safetensors",
|
| 551 |
+
"backbone.blocks.4.ffn.w3.bias": "model.safetensors",
|
| 552 |
+
"backbone.blocks.4.ffn.w3.biases": "model.safetensors",
|
| 553 |
+
"backbone.blocks.4.ffn.w3.scales": "model.safetensors",
|
| 554 |
+
"backbone.blocks.4.ffn.w3.weight": "model.safetensors",
|
| 555 |
+
"backbone.blocks.4.ln1.weight": "model.safetensors",
|
| 556 |
+
"backbone.blocks.4.ln2.weight": "model.safetensors",
|
| 557 |
+
"backbone.blocks.5.attn.gamma.weight": "model.safetensors",
|
| 558 |
+
"backbone.blocks.5.attn.k_norm.weight": "model.safetensors",
|
| 559 |
+
"backbone.blocks.5.attn.proj.bias": "model.safetensors",
|
| 560 |
+
"backbone.blocks.5.attn.proj.biases": "model.safetensors",
|
| 561 |
+
"backbone.blocks.5.attn.proj.scales": "model.safetensors",
|
| 562 |
+
"backbone.blocks.5.attn.proj.weight": "model.safetensors",
|
| 563 |
+
"backbone.blocks.5.attn.q_norm.weight": "model.safetensors",
|
| 564 |
+
"backbone.blocks.5.attn.wk.bias": "model.safetensors",
|
| 565 |
+
"backbone.blocks.5.attn.wk.biases": "model.safetensors",
|
| 566 |
+
"backbone.blocks.5.attn.wk.scales": "model.safetensors",
|
| 567 |
+
"backbone.blocks.5.attn.wk.weight": "model.safetensors",
|
| 568 |
+
"backbone.blocks.5.attn.wq.bias": "model.safetensors",
|
| 569 |
+
"backbone.blocks.5.attn.wq.biases": "model.safetensors",
|
| 570 |
+
"backbone.blocks.5.attn.wq.scales": "model.safetensors",
|
| 571 |
+
"backbone.blocks.5.attn.wq.weight": "model.safetensors",
|
| 572 |
+
"backbone.blocks.5.attn.wv.bias": "model.safetensors",
|
| 573 |
+
"backbone.blocks.5.attn.wv.biases": "model.safetensors",
|
| 574 |
+
"backbone.blocks.5.attn.wv.scales": "model.safetensors",
|
| 575 |
+
"backbone.blocks.5.attn.wv.weight": "model.safetensors",
|
| 576 |
+
"backbone.blocks.5.ffn.w12.bias": "model.safetensors",
|
| 577 |
+
"backbone.blocks.5.ffn.w12.biases": "model.safetensors",
|
| 578 |
+
"backbone.blocks.5.ffn.w12.scales": "model.safetensors",
|
| 579 |
+
"backbone.blocks.5.ffn.w12.weight": "model.safetensors",
|
| 580 |
+
"backbone.blocks.5.ffn.w3.bias": "model.safetensors",
|
| 581 |
+
"backbone.blocks.5.ffn.w3.biases": "model.safetensors",
|
| 582 |
+
"backbone.blocks.5.ffn.w3.scales": "model.safetensors",
|
| 583 |
+
"backbone.blocks.5.ffn.w3.weight": "model.safetensors",
|
| 584 |
+
"backbone.blocks.5.ln1.weight": "model.safetensors",
|
| 585 |
+
"backbone.blocks.5.ln2.weight": "model.safetensors",
|
| 586 |
+
"backbone.blocks.6.attn.gamma.weight": "model.safetensors",
|
| 587 |
+
"backbone.blocks.6.attn.k_norm.weight": "model.safetensors",
|
| 588 |
+
"backbone.blocks.6.attn.proj.bias": "model.safetensors",
|
| 589 |
+
"backbone.blocks.6.attn.proj.biases": "model.safetensors",
|
| 590 |
+
"backbone.blocks.6.attn.proj.scales": "model.safetensors",
|
| 591 |
+
"backbone.blocks.6.attn.proj.weight": "model.safetensors",
|
| 592 |
+
"backbone.blocks.6.attn.q_norm.weight": "model.safetensors",
|
| 593 |
+
"backbone.blocks.6.attn.wk.bias": "model.safetensors",
|
| 594 |
+
"backbone.blocks.6.attn.wk.biases": "model.safetensors",
|
| 595 |
+
"backbone.blocks.6.attn.wk.scales": "model.safetensors",
|
| 596 |
+
"backbone.blocks.6.attn.wk.weight": "model.safetensors",
|
| 597 |
+
"backbone.blocks.6.attn.wq.bias": "model.safetensors",
|
| 598 |
+
"backbone.blocks.6.attn.wq.biases": "model.safetensors",
|
| 599 |
+
"backbone.blocks.6.attn.wq.scales": "model.safetensors",
|
| 600 |
+
"backbone.blocks.6.attn.wq.weight": "model.safetensors",
|
| 601 |
+
"backbone.blocks.6.attn.wv.bias": "model.safetensors",
|
| 602 |
+
"backbone.blocks.6.attn.wv.biases": "model.safetensors",
|
| 603 |
+
"backbone.blocks.6.attn.wv.scales": "model.safetensors",
|
| 604 |
+
"backbone.blocks.6.attn.wv.weight": "model.safetensors",
|
| 605 |
+
"backbone.blocks.6.ffn.w12.bias": "model.safetensors",
|
| 606 |
+
"backbone.blocks.6.ffn.w12.biases": "model.safetensors",
|
| 607 |
+
"backbone.blocks.6.ffn.w12.scales": "model.safetensors",
|
| 608 |
+
"backbone.blocks.6.ffn.w12.weight": "model.safetensors",
|
| 609 |
+
"backbone.blocks.6.ffn.w3.bias": "model.safetensors",
|
| 610 |
+
"backbone.blocks.6.ffn.w3.biases": "model.safetensors",
|
| 611 |
+
"backbone.blocks.6.ffn.w3.scales": "model.safetensors",
|
| 612 |
+
"backbone.blocks.6.ffn.w3.weight": "model.safetensors",
|
| 613 |
+
"backbone.blocks.6.ln1.weight": "model.safetensors",
|
| 614 |
+
"backbone.blocks.6.ln2.weight": "model.safetensors",
|
| 615 |
+
"backbone.blocks.7.attn.gamma.weight": "model.safetensors",
|
| 616 |
+
"backbone.blocks.7.attn.k_norm.weight": "model.safetensors",
|
| 617 |
+
"backbone.blocks.7.attn.proj.bias": "model.safetensors",
|
| 618 |
+
"backbone.blocks.7.attn.proj.biases": "model.safetensors",
|
| 619 |
+
"backbone.blocks.7.attn.proj.scales": "model.safetensors",
|
| 620 |
+
"backbone.blocks.7.attn.proj.weight": "model.safetensors",
|
| 621 |
+
"backbone.blocks.7.attn.q_norm.weight": "model.safetensors",
|
| 622 |
+
"backbone.blocks.7.attn.wk.bias": "model.safetensors",
|
| 623 |
+
"backbone.blocks.7.attn.wk.biases": "model.safetensors",
|
| 624 |
+
"backbone.blocks.7.attn.wk.scales": "model.safetensors",
|
| 625 |
+
"backbone.blocks.7.attn.wk.weight": "model.safetensors",
|
| 626 |
+
"backbone.blocks.7.attn.wq.bias": "model.safetensors",
|
| 627 |
+
"backbone.blocks.7.attn.wq.biases": "model.safetensors",
|
| 628 |
+
"backbone.blocks.7.attn.wq.scales": "model.safetensors",
|
| 629 |
+
"backbone.blocks.7.attn.wq.weight": "model.safetensors",
|
| 630 |
+
"backbone.blocks.7.attn.wv.bias": "model.safetensors",
|
| 631 |
+
"backbone.blocks.7.attn.wv.biases": "model.safetensors",
|
| 632 |
+
"backbone.blocks.7.attn.wv.scales": "model.safetensors",
|
| 633 |
+
"backbone.blocks.7.attn.wv.weight": "model.safetensors",
|
| 634 |
+
"backbone.blocks.7.ffn.w12.bias": "model.safetensors",
|
| 635 |
+
"backbone.blocks.7.ffn.w12.biases": "model.safetensors",
|
| 636 |
+
"backbone.blocks.7.ffn.w12.scales": "model.safetensors",
|
| 637 |
+
"backbone.blocks.7.ffn.w12.weight": "model.safetensors",
|
| 638 |
+
"backbone.blocks.7.ffn.w3.bias": "model.safetensors",
|
| 639 |
+
"backbone.blocks.7.ffn.w3.biases": "model.safetensors",
|
| 640 |
+
"backbone.blocks.7.ffn.w3.scales": "model.safetensors",
|
| 641 |
+
"backbone.blocks.7.ffn.w3.weight": "model.safetensors",
|
| 642 |
+
"backbone.blocks.7.ln1.weight": "model.safetensors",
|
| 643 |
+
"backbone.blocks.7.ln2.weight": "model.safetensors",
|
| 644 |
+
"backbone.blocks.8.attn.gamma.weight": "model.safetensors",
|
| 645 |
+
"backbone.blocks.8.attn.k_norm.weight": "model.safetensors",
|
| 646 |
+
"backbone.blocks.8.attn.proj.bias": "model.safetensors",
|
| 647 |
+
"backbone.blocks.8.attn.proj.biases": "model.safetensors",
|
| 648 |
+
"backbone.blocks.8.attn.proj.scales": "model.safetensors",
|
| 649 |
+
"backbone.blocks.8.attn.proj.weight": "model.safetensors",
|
| 650 |
+
"backbone.blocks.8.attn.q_norm.weight": "model.safetensors",
|
| 651 |
+
"backbone.blocks.8.attn.wk.bias": "model.safetensors",
|
| 652 |
+
"backbone.blocks.8.attn.wk.biases": "model.safetensors",
|
| 653 |
+
"backbone.blocks.8.attn.wk.scales": "model.safetensors",
|
| 654 |
+
"backbone.blocks.8.attn.wk.weight": "model.safetensors",
|
| 655 |
+
"backbone.blocks.8.attn.wq.bias": "model.safetensors",
|
| 656 |
+
"backbone.blocks.8.attn.wq.biases": "model.safetensors",
|
| 657 |
+
"backbone.blocks.8.attn.wq.scales": "model.safetensors",
|
| 658 |
+
"backbone.blocks.8.attn.wq.weight": "model.safetensors",
|
| 659 |
+
"backbone.blocks.8.attn.wv.bias": "model.safetensors",
|
| 660 |
+
"backbone.blocks.8.attn.wv.biases": "model.safetensors",
|
| 661 |
+
"backbone.blocks.8.attn.wv.scales": "model.safetensors",
|
| 662 |
+
"backbone.blocks.8.attn.wv.weight": "model.safetensors",
|
| 663 |
+
"backbone.blocks.8.ffn.w12.bias": "model.safetensors",
|
| 664 |
+
"backbone.blocks.8.ffn.w12.biases": "model.safetensors",
|
| 665 |
+
"backbone.blocks.8.ffn.w12.scales": "model.safetensors",
|
| 666 |
+
"backbone.blocks.8.ffn.w12.weight": "model.safetensors",
|
| 667 |
+
"backbone.blocks.8.ffn.w3.bias": "model.safetensors",
|
| 668 |
+
"backbone.blocks.8.ffn.w3.biases": "model.safetensors",
|
| 669 |
+
"backbone.blocks.8.ffn.w3.scales": "model.safetensors",
|
| 670 |
+
"backbone.blocks.8.ffn.w3.weight": "model.safetensors",
|
| 671 |
+
"backbone.blocks.8.ln1.weight": "model.safetensors",
|
| 672 |
+
"backbone.blocks.8.ln2.weight": "model.safetensors",
|
| 673 |
+
"backbone.blocks.9.attn.gamma.weight": "model.safetensors",
|
| 674 |
+
"backbone.blocks.9.attn.k_norm.weight": "model.safetensors",
|
| 675 |
+
"backbone.blocks.9.attn.proj.bias": "model.safetensors",
|
| 676 |
+
"backbone.blocks.9.attn.proj.biases": "model.safetensors",
|
| 677 |
+
"backbone.blocks.9.attn.proj.scales": "model.safetensors",
|
| 678 |
+
"backbone.blocks.9.attn.proj.weight": "model.safetensors",
|
| 679 |
+
"backbone.blocks.9.attn.q_norm.weight": "model.safetensors",
|
| 680 |
+
"backbone.blocks.9.attn.wk.bias": "model.safetensors",
|
| 681 |
+
"backbone.blocks.9.attn.wk.biases": "model.safetensors",
|
| 682 |
+
"backbone.blocks.9.attn.wk.scales": "model.safetensors",
|
| 683 |
+
"backbone.blocks.9.attn.wk.weight": "model.safetensors",
|
| 684 |
+
"backbone.blocks.9.attn.wq.bias": "model.safetensors",
|
| 685 |
+
"backbone.blocks.9.attn.wq.biases": "model.safetensors",
|
| 686 |
+
"backbone.blocks.9.attn.wq.scales": "model.safetensors",
|
| 687 |
+
"backbone.blocks.9.attn.wq.weight": "model.safetensors",
|
| 688 |
+
"backbone.blocks.9.attn.wv.bias": "model.safetensors",
|
| 689 |
+
"backbone.blocks.9.attn.wv.biases": "model.safetensors",
|
| 690 |
+
"backbone.blocks.9.attn.wv.scales": "model.safetensors",
|
| 691 |
+
"backbone.blocks.9.attn.wv.weight": "model.safetensors",
|
| 692 |
+
"backbone.blocks.9.ffn.w12.bias": "model.safetensors",
|
| 693 |
+
"backbone.blocks.9.ffn.w12.biases": "model.safetensors",
|
| 694 |
+
"backbone.blocks.9.ffn.w12.scales": "model.safetensors",
|
| 695 |
+
"backbone.blocks.9.ffn.w12.weight": "model.safetensors",
|
| 696 |
+
"backbone.blocks.9.ffn.w3.bias": "model.safetensors",
|
| 697 |
+
"backbone.blocks.9.ffn.w3.biases": "model.safetensors",
|
| 698 |
+
"backbone.blocks.9.ffn.w3.scales": "model.safetensors",
|
| 699 |
+
"backbone.blocks.9.ffn.w3.weight": "model.safetensors",
|
| 700 |
+
"backbone.blocks.9.ln1.weight": "model.safetensors",
|
| 701 |
+
"backbone.blocks.9.ln2.weight": "model.safetensors",
|
| 702 |
+
"backbone.cls_token": "model.safetensors",
|
| 703 |
+
"backbone.ln1.weight": "model.safetensors",
|
| 704 |
+
"backbone.patch_embed.projection.bias": "model.safetensors",
|
| 705 |
+
"backbone.patch_embed.projection.weight": "model.safetensors",
|
| 706 |
+
"backbone.rope_embed.periods": "model.safetensors",
|
| 707 |
+
"backbone.storage_tokens": "model.safetensors",
|
| 708 |
+
"decode_head.conv_layers.0.bias": "model.safetensors",
|
| 709 |
+
"decode_head.conv_layers.0.weight": "model.safetensors",
|
| 710 |
+
"decode_head.conv_layers.3.bias": "model.safetensors",
|
| 711 |
+
"decode_head.conv_layers.3.weight": "model.safetensors",
|
| 712 |
+
"decode_head.conv_seg.bias": "model.safetensors",
|
| 713 |
+
"decode_head.conv_seg.weight": "model.safetensors",
|
| 714 |
+
"decode_head.deconv_layers.0.weight": "model.safetensors",
|
| 715 |
+
"decode_head.deconv_layers.3.weight": "model.safetensors",
|
| 716 |
+
"decode_head.deconv_layers.6.weight": "model.safetensors",
|
| 717 |
+
"decode_head.deconv_layers.9.weight": "model.safetensors"
|
| 718 |
+
}
|
| 719 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_size": [
|
| 3 |
+
1024,
|
| 4 |
+
768
|
| 5 |
+
],
|
| 6 |
+
"image_mean": [
|
| 7 |
+
123.67500305175781,
|
| 8 |
+
116.27999877929688,
|
| 9 |
+
103.52999877929688
|
| 10 |
+
],
|
| 11 |
+
"image_std": [
|
| 12 |
+
58.39500045776367,
|
| 13 |
+
57.119998931884766,
|
| 14 |
+
57.375
|
| 15 |
+
]
|
| 16 |
+
}
|