Upload folder using huggingface_hub
Browse files- checkpoints/.DS_Store +0 -0
- checkpoints/SD1.5/.DS_Store +0 -0
- checkpoints/SD1.5/DreamShaper.safetensors +3 -0
- checkpoints/SD1.5/MeinaMix.safetensors +3 -0
- checkpoints/SD1.5/ghostmix_v20Bakedvae.safetensors +3 -0
- checkpoints/SD1.5/majicMIX_realistic.safetensors +3 -0
- checkpoints/SD1.5/realisticVisionV60B1_v51VAE.safetensors +3 -0
- configs/anything_v3.yaml +73 -0
- configs/v1-inference.yaml +70 -0
- configs/v1-inference_clip_skip_2.yaml +73 -0
- configs/v1-inference_clip_skip_2_fp16.yaml +74 -0
- configs/v1-inference_fp16.yaml +71 -0
- configs/v1-inpainting-inference.yaml +71 -0
- configs/v2-inference-v.yaml +68 -0
- configs/v2-inference-v_fp32.yaml +68 -0
- configs/v2-inference.yaml +67 -0
- configs/v2-inference_fp32.yaml +67 -0
- configs/v2-inpainting-inference.yaml +158 -0
- controlnet/color_finetune.safetensors +3 -0
- controlnet/control_v11p_sd15_scribble.safetensors +3 -0
- inpaint/brushnet/random_mask_brushnet_ckpt/config.json +58 -0
- inpaint/brushnet/random_mask_brushnet_ckpt/diffusion_pytorch_model.safetensors +3 -0
- inpaint/brushnet/segmentation_mask_brushnet_ckpt/config.json +58 -0
- inpaint/brushnet/segmentation_mask_brushnet_ckpt/diffusion_pytorch_model.safetensors +3 -0
- llava-v1.5-7b-finetune-clean/config.json +49 -0
- llava-v1.5-7b-finetune-clean/generation_config.json +7 -0
- llava-v1.5-7b-finetune-clean/model-00001-of-00003.safetensors +3 -0
- llava-v1.5-7b-finetune-clean/model-00002-of-00003.safetensors +3 -0
- llava-v1.5-7b-finetune-clean/model-00003-of-00003.safetensors +3 -0
- llava-v1.5-7b-finetune-clean/model.safetensors.index.json +693 -0
- llava-v1.5-7b-finetune-clean/special_tokens_map.json +30 -0
- llava-v1.5-7b-finetune-clean/tokenizer.model +3 -0
- llava-v1.5-7b-finetune-clean/tokenizer_config.json +42 -0
- preprocessor/sk_model.pth +3 -0
- preprocessor/sk_model2.pth +3 -0
checkpoints/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
checkpoints/SD1.5/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
checkpoints/SD1.5/DreamShaper.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:879db523c30d3b9017143d56705015e15a2cb5628762c11d086fed9538abd7fd
|
| 3 |
+
size 2132625894
|
checkpoints/SD1.5/MeinaMix.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54ef3e3610eee7f0f6c9f9b82eee26aa404598512d800494d1db344e3bc560b1
|
| 3 |
+
size 2132651818
|
checkpoints/SD1.5/ghostmix_v20Bakedvae.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3edb8a26f44dfddc124129004b5ded3378be974b8d3bf82f43b9660d416d3d1
|
| 3 |
+
size 2400065384
|
checkpoints/SD1.5/majicMIX_realistic.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c819b6d13663ed720c2254f4fe18373107dfef2448d337913c8fc545640881e
|
| 3 |
+
size 2132625894
|
checkpoints/SD1.5/realisticVisionV60B1_v51VAE.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15012c538f503ce2ebfc2c8547b268c75ccdaff7a281db55399940ff1d70e21d
|
| 3 |
+
size 2132625894
|
configs/anything_v3.yaml
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-04
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false # Note: different from the one we trained before
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False
|
| 19 |
+
|
| 20 |
+
scheduler_config: # 10000 warmup steps
|
| 21 |
+
target: ldm.lr_scheduler.LambdaLinearScheduler
|
| 22 |
+
params:
|
| 23 |
+
warm_up_steps: [ 10000 ]
|
| 24 |
+
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
| 25 |
+
f_start: [ 1.e-6 ]
|
| 26 |
+
f_max: [ 1. ]
|
| 27 |
+
f_min: [ 1. ]
|
| 28 |
+
|
| 29 |
+
unet_config:
|
| 30 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 31 |
+
params:
|
| 32 |
+
image_size: 32 # unused
|
| 33 |
+
in_channels: 4
|
| 34 |
+
out_channels: 4
|
| 35 |
+
model_channels: 320
|
| 36 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 37 |
+
num_res_blocks: 2
|
| 38 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 39 |
+
num_heads: 8
|
| 40 |
+
use_spatial_transformer: True
|
| 41 |
+
transformer_depth: 1
|
| 42 |
+
context_dim: 768
|
| 43 |
+
use_checkpoint: True
|
| 44 |
+
legacy: False
|
| 45 |
+
|
| 46 |
+
first_stage_config:
|
| 47 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 48 |
+
params:
|
| 49 |
+
embed_dim: 4
|
| 50 |
+
monitor: val/rec_loss
|
| 51 |
+
ddconfig:
|
| 52 |
+
double_z: true
|
| 53 |
+
z_channels: 4
|
| 54 |
+
resolution: 256
|
| 55 |
+
in_channels: 3
|
| 56 |
+
out_ch: 3
|
| 57 |
+
ch: 128
|
| 58 |
+
ch_mult:
|
| 59 |
+
- 1
|
| 60 |
+
- 2
|
| 61 |
+
- 4
|
| 62 |
+
- 4
|
| 63 |
+
num_res_blocks: 2
|
| 64 |
+
attn_resolutions: []
|
| 65 |
+
dropout: 0.0
|
| 66 |
+
lossconfig:
|
| 67 |
+
target: torch.nn.Identity
|
| 68 |
+
|
| 69 |
+
cond_stage_config:
|
| 70 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
| 71 |
+
params:
|
| 72 |
+
layer: "hidden"
|
| 73 |
+
layer_idx: -2
|
configs/v1-inference.yaml
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-04
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false # Note: different from the one we trained before
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False
|
| 19 |
+
|
| 20 |
+
scheduler_config: # 10000 warmup steps
|
| 21 |
+
target: ldm.lr_scheduler.LambdaLinearScheduler
|
| 22 |
+
params:
|
| 23 |
+
warm_up_steps: [ 10000 ]
|
| 24 |
+
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
| 25 |
+
f_start: [ 1.e-6 ]
|
| 26 |
+
f_max: [ 1. ]
|
| 27 |
+
f_min: [ 1. ]
|
| 28 |
+
|
| 29 |
+
unet_config:
|
| 30 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 31 |
+
params:
|
| 32 |
+
image_size: 32 # unused
|
| 33 |
+
in_channels: 4
|
| 34 |
+
out_channels: 4
|
| 35 |
+
model_channels: 320
|
| 36 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 37 |
+
num_res_blocks: 2
|
| 38 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 39 |
+
num_heads: 8
|
| 40 |
+
use_spatial_transformer: True
|
| 41 |
+
transformer_depth: 1
|
| 42 |
+
context_dim: 768
|
| 43 |
+
use_checkpoint: True
|
| 44 |
+
legacy: False
|
| 45 |
+
|
| 46 |
+
first_stage_config:
|
| 47 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 48 |
+
params:
|
| 49 |
+
embed_dim: 4
|
| 50 |
+
monitor: val/rec_loss
|
| 51 |
+
ddconfig:
|
| 52 |
+
double_z: true
|
| 53 |
+
z_channels: 4
|
| 54 |
+
resolution: 256
|
| 55 |
+
in_channels: 3
|
| 56 |
+
out_ch: 3
|
| 57 |
+
ch: 128
|
| 58 |
+
ch_mult:
|
| 59 |
+
- 1
|
| 60 |
+
- 2
|
| 61 |
+
- 4
|
| 62 |
+
- 4
|
| 63 |
+
num_res_blocks: 2
|
| 64 |
+
attn_resolutions: []
|
| 65 |
+
dropout: 0.0
|
| 66 |
+
lossconfig:
|
| 67 |
+
target: torch.nn.Identity
|
| 68 |
+
|
| 69 |
+
cond_stage_config:
|
| 70 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
configs/v1-inference_clip_skip_2.yaml
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-04
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false # Note: different from the one we trained before
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False
|
| 19 |
+
|
| 20 |
+
scheduler_config: # 10000 warmup steps
|
| 21 |
+
target: ldm.lr_scheduler.LambdaLinearScheduler
|
| 22 |
+
params:
|
| 23 |
+
warm_up_steps: [ 10000 ]
|
| 24 |
+
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
| 25 |
+
f_start: [ 1.e-6 ]
|
| 26 |
+
f_max: [ 1. ]
|
| 27 |
+
f_min: [ 1. ]
|
| 28 |
+
|
| 29 |
+
unet_config:
|
| 30 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 31 |
+
params:
|
| 32 |
+
image_size: 32 # unused
|
| 33 |
+
in_channels: 4
|
| 34 |
+
out_channels: 4
|
| 35 |
+
model_channels: 320
|
| 36 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 37 |
+
num_res_blocks: 2
|
| 38 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 39 |
+
num_heads: 8
|
| 40 |
+
use_spatial_transformer: True
|
| 41 |
+
transformer_depth: 1
|
| 42 |
+
context_dim: 768
|
| 43 |
+
use_checkpoint: True
|
| 44 |
+
legacy: False
|
| 45 |
+
|
| 46 |
+
first_stage_config:
|
| 47 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 48 |
+
params:
|
| 49 |
+
embed_dim: 4
|
| 50 |
+
monitor: val/rec_loss
|
| 51 |
+
ddconfig:
|
| 52 |
+
double_z: true
|
| 53 |
+
z_channels: 4
|
| 54 |
+
resolution: 256
|
| 55 |
+
in_channels: 3
|
| 56 |
+
out_ch: 3
|
| 57 |
+
ch: 128
|
| 58 |
+
ch_mult:
|
| 59 |
+
- 1
|
| 60 |
+
- 2
|
| 61 |
+
- 4
|
| 62 |
+
- 4
|
| 63 |
+
num_res_blocks: 2
|
| 64 |
+
attn_resolutions: []
|
| 65 |
+
dropout: 0.0
|
| 66 |
+
lossconfig:
|
| 67 |
+
target: torch.nn.Identity
|
| 68 |
+
|
| 69 |
+
cond_stage_config:
|
| 70 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
| 71 |
+
params:
|
| 72 |
+
layer: "hidden"
|
| 73 |
+
layer_idx: -2
|
configs/v1-inference_clip_skip_2_fp16.yaml
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-04
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false # Note: different from the one we trained before
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False
|
| 19 |
+
|
| 20 |
+
scheduler_config: # 10000 warmup steps
|
| 21 |
+
target: ldm.lr_scheduler.LambdaLinearScheduler
|
| 22 |
+
params:
|
| 23 |
+
warm_up_steps: [ 10000 ]
|
| 24 |
+
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
| 25 |
+
f_start: [ 1.e-6 ]
|
| 26 |
+
f_max: [ 1. ]
|
| 27 |
+
f_min: [ 1. ]
|
| 28 |
+
|
| 29 |
+
unet_config:
|
| 30 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 31 |
+
params:
|
| 32 |
+
use_fp16: True
|
| 33 |
+
image_size: 32 # unused
|
| 34 |
+
in_channels: 4
|
| 35 |
+
out_channels: 4
|
| 36 |
+
model_channels: 320
|
| 37 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 38 |
+
num_res_blocks: 2
|
| 39 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 40 |
+
num_heads: 8
|
| 41 |
+
use_spatial_transformer: True
|
| 42 |
+
transformer_depth: 1
|
| 43 |
+
context_dim: 768
|
| 44 |
+
use_checkpoint: True
|
| 45 |
+
legacy: False
|
| 46 |
+
|
| 47 |
+
first_stage_config:
|
| 48 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 49 |
+
params:
|
| 50 |
+
embed_dim: 4
|
| 51 |
+
monitor: val/rec_loss
|
| 52 |
+
ddconfig:
|
| 53 |
+
double_z: true
|
| 54 |
+
z_channels: 4
|
| 55 |
+
resolution: 256
|
| 56 |
+
in_channels: 3
|
| 57 |
+
out_ch: 3
|
| 58 |
+
ch: 128
|
| 59 |
+
ch_mult:
|
| 60 |
+
- 1
|
| 61 |
+
- 2
|
| 62 |
+
- 4
|
| 63 |
+
- 4
|
| 64 |
+
num_res_blocks: 2
|
| 65 |
+
attn_resolutions: []
|
| 66 |
+
dropout: 0.0
|
| 67 |
+
lossconfig:
|
| 68 |
+
target: torch.nn.Identity
|
| 69 |
+
|
| 70 |
+
cond_stage_config:
|
| 71 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
| 72 |
+
params:
|
| 73 |
+
layer: "hidden"
|
| 74 |
+
layer_idx: -2
|
configs/v1-inference_fp16.yaml
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-04
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false # Note: different from the one we trained before
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False
|
| 19 |
+
|
| 20 |
+
scheduler_config: # 10000 warmup steps
|
| 21 |
+
target: ldm.lr_scheduler.LambdaLinearScheduler
|
| 22 |
+
params:
|
| 23 |
+
warm_up_steps: [ 10000 ]
|
| 24 |
+
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
| 25 |
+
f_start: [ 1.e-6 ]
|
| 26 |
+
f_max: [ 1. ]
|
| 27 |
+
f_min: [ 1. ]
|
| 28 |
+
|
| 29 |
+
unet_config:
|
| 30 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 31 |
+
params:
|
| 32 |
+
use_fp16: True
|
| 33 |
+
image_size: 32 # unused
|
| 34 |
+
in_channels: 4
|
| 35 |
+
out_channels: 4
|
| 36 |
+
model_channels: 320
|
| 37 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 38 |
+
num_res_blocks: 2
|
| 39 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 40 |
+
num_heads: 8
|
| 41 |
+
use_spatial_transformer: True
|
| 42 |
+
transformer_depth: 1
|
| 43 |
+
context_dim: 768
|
| 44 |
+
use_checkpoint: True
|
| 45 |
+
legacy: False
|
| 46 |
+
|
| 47 |
+
first_stage_config:
|
| 48 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 49 |
+
params:
|
| 50 |
+
embed_dim: 4
|
| 51 |
+
monitor: val/rec_loss
|
| 52 |
+
ddconfig:
|
| 53 |
+
double_z: true
|
| 54 |
+
z_channels: 4
|
| 55 |
+
resolution: 256
|
| 56 |
+
in_channels: 3
|
| 57 |
+
out_ch: 3
|
| 58 |
+
ch: 128
|
| 59 |
+
ch_mult:
|
| 60 |
+
- 1
|
| 61 |
+
- 2
|
| 62 |
+
- 4
|
| 63 |
+
- 4
|
| 64 |
+
num_res_blocks: 2
|
| 65 |
+
attn_resolutions: []
|
| 66 |
+
dropout: 0.0
|
| 67 |
+
lossconfig:
|
| 68 |
+
target: torch.nn.Identity
|
| 69 |
+
|
| 70 |
+
cond_stage_config:
|
| 71 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
configs/v1-inpainting-inference.yaml
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 7.5e-05
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false # Note: different from the one we trained before
|
| 15 |
+
conditioning_key: hybrid # important
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
finetune_keys: null
|
| 19 |
+
|
| 20 |
+
scheduler_config: # 10000 warmup steps
|
| 21 |
+
target: ldm.lr_scheduler.LambdaLinearScheduler
|
| 22 |
+
params:
|
| 23 |
+
warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
|
| 24 |
+
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
| 25 |
+
f_start: [ 1.e-6 ]
|
| 26 |
+
f_max: [ 1. ]
|
| 27 |
+
f_min: [ 1. ]
|
| 28 |
+
|
| 29 |
+
unet_config:
|
| 30 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 31 |
+
params:
|
| 32 |
+
image_size: 32 # unused
|
| 33 |
+
in_channels: 9 # 4 data + 4 downscaled image + 1 mask
|
| 34 |
+
out_channels: 4
|
| 35 |
+
model_channels: 320
|
| 36 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 37 |
+
num_res_blocks: 2
|
| 38 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 39 |
+
num_heads: 8
|
| 40 |
+
use_spatial_transformer: True
|
| 41 |
+
transformer_depth: 1
|
| 42 |
+
context_dim: 768
|
| 43 |
+
use_checkpoint: True
|
| 44 |
+
legacy: False
|
| 45 |
+
|
| 46 |
+
first_stage_config:
|
| 47 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 48 |
+
params:
|
| 49 |
+
embed_dim: 4
|
| 50 |
+
monitor: val/rec_loss
|
| 51 |
+
ddconfig:
|
| 52 |
+
double_z: true
|
| 53 |
+
z_channels: 4
|
| 54 |
+
resolution: 256
|
| 55 |
+
in_channels: 3
|
| 56 |
+
out_ch: 3
|
| 57 |
+
ch: 128
|
| 58 |
+
ch_mult:
|
| 59 |
+
- 1
|
| 60 |
+
- 2
|
| 61 |
+
- 4
|
| 62 |
+
- 4
|
| 63 |
+
num_res_blocks: 2
|
| 64 |
+
attn_resolutions: []
|
| 65 |
+
dropout: 0.0
|
| 66 |
+
lossconfig:
|
| 67 |
+
target: torch.nn.Identity
|
| 68 |
+
|
| 69 |
+
cond_stage_config:
|
| 70 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
| 71 |
+
|
configs/v2-inference-v.yaml
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-4
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
parameterization: "v"
|
| 6 |
+
linear_start: 0.00085
|
| 7 |
+
linear_end: 0.0120
|
| 8 |
+
num_timesteps_cond: 1
|
| 9 |
+
log_every_t: 200
|
| 10 |
+
timesteps: 1000
|
| 11 |
+
first_stage_key: "jpg"
|
| 12 |
+
cond_stage_key: "txt"
|
| 13 |
+
image_size: 64
|
| 14 |
+
channels: 4
|
| 15 |
+
cond_stage_trainable: false
|
| 16 |
+
conditioning_key: crossattn
|
| 17 |
+
monitor: val/loss_simple_ema
|
| 18 |
+
scale_factor: 0.18215
|
| 19 |
+
use_ema: False # we set this to false because this is an inference only config
|
| 20 |
+
|
| 21 |
+
unet_config:
|
| 22 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 23 |
+
params:
|
| 24 |
+
use_checkpoint: True
|
| 25 |
+
use_fp16: True
|
| 26 |
+
image_size: 32 # unused
|
| 27 |
+
in_channels: 4
|
| 28 |
+
out_channels: 4
|
| 29 |
+
model_channels: 320
|
| 30 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 31 |
+
num_res_blocks: 2
|
| 32 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 33 |
+
num_head_channels: 64 # need to fix for flash-attn
|
| 34 |
+
use_spatial_transformer: True
|
| 35 |
+
use_linear_in_transformer: True
|
| 36 |
+
transformer_depth: 1
|
| 37 |
+
context_dim: 1024
|
| 38 |
+
legacy: False
|
| 39 |
+
|
| 40 |
+
first_stage_config:
|
| 41 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 42 |
+
params:
|
| 43 |
+
embed_dim: 4
|
| 44 |
+
monitor: val/rec_loss
|
| 45 |
+
ddconfig:
|
| 46 |
+
#attn_type: "vanilla-xformers"
|
| 47 |
+
double_z: true
|
| 48 |
+
z_channels: 4
|
| 49 |
+
resolution: 256
|
| 50 |
+
in_channels: 3
|
| 51 |
+
out_ch: 3
|
| 52 |
+
ch: 128
|
| 53 |
+
ch_mult:
|
| 54 |
+
- 1
|
| 55 |
+
- 2
|
| 56 |
+
- 4
|
| 57 |
+
- 4
|
| 58 |
+
num_res_blocks: 2
|
| 59 |
+
attn_resolutions: []
|
| 60 |
+
dropout: 0.0
|
| 61 |
+
lossconfig:
|
| 62 |
+
target: torch.nn.Identity
|
| 63 |
+
|
| 64 |
+
cond_stage_config:
|
| 65 |
+
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
| 66 |
+
params:
|
| 67 |
+
freeze: True
|
| 68 |
+
layer: "penultimate"
|
configs/v2-inference-v_fp32.yaml
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-4
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
parameterization: "v"
|
| 6 |
+
linear_start: 0.00085
|
| 7 |
+
linear_end: 0.0120
|
| 8 |
+
num_timesteps_cond: 1
|
| 9 |
+
log_every_t: 200
|
| 10 |
+
timesteps: 1000
|
| 11 |
+
first_stage_key: "jpg"
|
| 12 |
+
cond_stage_key: "txt"
|
| 13 |
+
image_size: 64
|
| 14 |
+
channels: 4
|
| 15 |
+
cond_stage_trainable: false
|
| 16 |
+
conditioning_key: crossattn
|
| 17 |
+
monitor: val/loss_simple_ema
|
| 18 |
+
scale_factor: 0.18215
|
| 19 |
+
use_ema: False # we set this to false because this is an inference only config
|
| 20 |
+
|
| 21 |
+
unet_config:
|
| 22 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 23 |
+
params:
|
| 24 |
+
use_checkpoint: True
|
| 25 |
+
use_fp16: False
|
| 26 |
+
image_size: 32 # unused
|
| 27 |
+
in_channels: 4
|
| 28 |
+
out_channels: 4
|
| 29 |
+
model_channels: 320
|
| 30 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 31 |
+
num_res_blocks: 2
|
| 32 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 33 |
+
num_head_channels: 64 # need to fix for flash-attn
|
| 34 |
+
use_spatial_transformer: True
|
| 35 |
+
use_linear_in_transformer: True
|
| 36 |
+
transformer_depth: 1
|
| 37 |
+
context_dim: 1024
|
| 38 |
+
legacy: False
|
| 39 |
+
|
| 40 |
+
first_stage_config:
|
| 41 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 42 |
+
params:
|
| 43 |
+
embed_dim: 4
|
| 44 |
+
monitor: val/rec_loss
|
| 45 |
+
ddconfig:
|
| 46 |
+
#attn_type: "vanilla-xformers"
|
| 47 |
+
double_z: true
|
| 48 |
+
z_channels: 4
|
| 49 |
+
resolution: 256
|
| 50 |
+
in_channels: 3
|
| 51 |
+
out_ch: 3
|
| 52 |
+
ch: 128
|
| 53 |
+
ch_mult:
|
| 54 |
+
- 1
|
| 55 |
+
- 2
|
| 56 |
+
- 4
|
| 57 |
+
- 4
|
| 58 |
+
num_res_blocks: 2
|
| 59 |
+
attn_resolutions: []
|
| 60 |
+
dropout: 0.0
|
| 61 |
+
lossconfig:
|
| 62 |
+
target: torch.nn.Identity
|
| 63 |
+
|
| 64 |
+
cond_stage_config:
|
| 65 |
+
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
| 66 |
+
params:
|
| 67 |
+
freeze: True
|
| 68 |
+
layer: "penultimate"
|
configs/v2-inference.yaml
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-4
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False # we set this to false because this is an inference only config
|
| 19 |
+
|
| 20 |
+
unet_config:
|
| 21 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 22 |
+
params:
|
| 23 |
+
use_checkpoint: True
|
| 24 |
+
use_fp16: True
|
| 25 |
+
image_size: 32 # unused
|
| 26 |
+
in_channels: 4
|
| 27 |
+
out_channels: 4
|
| 28 |
+
model_channels: 320
|
| 29 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 30 |
+
num_res_blocks: 2
|
| 31 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 32 |
+
num_head_channels: 64 # need to fix for flash-attn
|
| 33 |
+
use_spatial_transformer: True
|
| 34 |
+
use_linear_in_transformer: True
|
| 35 |
+
transformer_depth: 1
|
| 36 |
+
context_dim: 1024
|
| 37 |
+
legacy: False
|
| 38 |
+
|
| 39 |
+
first_stage_config:
|
| 40 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 41 |
+
params:
|
| 42 |
+
embed_dim: 4
|
| 43 |
+
monitor: val/rec_loss
|
| 44 |
+
ddconfig:
|
| 45 |
+
#attn_type: "vanilla-xformers"
|
| 46 |
+
double_z: true
|
| 47 |
+
z_channels: 4
|
| 48 |
+
resolution: 256
|
| 49 |
+
in_channels: 3
|
| 50 |
+
out_ch: 3
|
| 51 |
+
ch: 128
|
| 52 |
+
ch_mult:
|
| 53 |
+
- 1
|
| 54 |
+
- 2
|
| 55 |
+
- 4
|
| 56 |
+
- 4
|
| 57 |
+
num_res_blocks: 2
|
| 58 |
+
attn_resolutions: []
|
| 59 |
+
dropout: 0.0
|
| 60 |
+
lossconfig:
|
| 61 |
+
target: torch.nn.Identity
|
| 62 |
+
|
| 63 |
+
cond_stage_config:
|
| 64 |
+
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
| 65 |
+
params:
|
| 66 |
+
freeze: True
|
| 67 |
+
layer: "penultimate"
|
configs/v2-inference_fp32.yaml
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 1.0e-4
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false
|
| 15 |
+
conditioning_key: crossattn
|
| 16 |
+
monitor: val/loss_simple_ema
|
| 17 |
+
scale_factor: 0.18215
|
| 18 |
+
use_ema: False # we set this to false because this is an inference only config
|
| 19 |
+
|
| 20 |
+
unet_config:
|
| 21 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 22 |
+
params:
|
| 23 |
+
use_checkpoint: True
|
| 24 |
+
use_fp16: False
|
| 25 |
+
image_size: 32 # unused
|
| 26 |
+
in_channels: 4
|
| 27 |
+
out_channels: 4
|
| 28 |
+
model_channels: 320
|
| 29 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 30 |
+
num_res_blocks: 2
|
| 31 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 32 |
+
num_head_channels: 64 # need to fix for flash-attn
|
| 33 |
+
use_spatial_transformer: True
|
| 34 |
+
use_linear_in_transformer: True
|
| 35 |
+
transformer_depth: 1
|
| 36 |
+
context_dim: 1024
|
| 37 |
+
legacy: False
|
| 38 |
+
|
| 39 |
+
first_stage_config:
|
| 40 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 41 |
+
params:
|
| 42 |
+
embed_dim: 4
|
| 43 |
+
monitor: val/rec_loss
|
| 44 |
+
ddconfig:
|
| 45 |
+
#attn_type: "vanilla-xformers"
|
| 46 |
+
double_z: true
|
| 47 |
+
z_channels: 4
|
| 48 |
+
resolution: 256
|
| 49 |
+
in_channels: 3
|
| 50 |
+
out_ch: 3
|
| 51 |
+
ch: 128
|
| 52 |
+
ch_mult:
|
| 53 |
+
- 1
|
| 54 |
+
- 2
|
| 55 |
+
- 4
|
| 56 |
+
- 4
|
| 57 |
+
num_res_blocks: 2
|
| 58 |
+
attn_resolutions: []
|
| 59 |
+
dropout: 0.0
|
| 60 |
+
lossconfig:
|
| 61 |
+
target: torch.nn.Identity
|
| 62 |
+
|
| 63 |
+
cond_stage_config:
|
| 64 |
+
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
| 65 |
+
params:
|
| 66 |
+
freeze: True
|
| 67 |
+
layer: "penultimate"
|
configs/v2-inpainting-inference.yaml
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
base_learning_rate: 5.0e-05
|
| 3 |
+
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
|
| 4 |
+
params:
|
| 5 |
+
linear_start: 0.00085
|
| 6 |
+
linear_end: 0.0120
|
| 7 |
+
num_timesteps_cond: 1
|
| 8 |
+
log_every_t: 200
|
| 9 |
+
timesteps: 1000
|
| 10 |
+
first_stage_key: "jpg"
|
| 11 |
+
cond_stage_key: "txt"
|
| 12 |
+
image_size: 64
|
| 13 |
+
channels: 4
|
| 14 |
+
cond_stage_trainable: false
|
| 15 |
+
conditioning_key: hybrid
|
| 16 |
+
scale_factor: 0.18215
|
| 17 |
+
monitor: val/loss_simple_ema
|
| 18 |
+
finetune_keys: null
|
| 19 |
+
use_ema: False
|
| 20 |
+
|
| 21 |
+
unet_config:
|
| 22 |
+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
| 23 |
+
params:
|
| 24 |
+
use_checkpoint: True
|
| 25 |
+
image_size: 32 # unused
|
| 26 |
+
in_channels: 9
|
| 27 |
+
out_channels: 4
|
| 28 |
+
model_channels: 320
|
| 29 |
+
attention_resolutions: [ 4, 2, 1 ]
|
| 30 |
+
num_res_blocks: 2
|
| 31 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
| 32 |
+
num_head_channels: 64 # need to fix for flash-attn
|
| 33 |
+
use_spatial_transformer: True
|
| 34 |
+
use_linear_in_transformer: True
|
| 35 |
+
transformer_depth: 1
|
| 36 |
+
context_dim: 1024
|
| 37 |
+
legacy: False
|
| 38 |
+
|
| 39 |
+
first_stage_config:
|
| 40 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
| 41 |
+
params:
|
| 42 |
+
embed_dim: 4
|
| 43 |
+
monitor: val/rec_loss
|
| 44 |
+
ddconfig:
|
| 45 |
+
#attn_type: "vanilla-xformers"
|
| 46 |
+
double_z: true
|
| 47 |
+
z_channels: 4
|
| 48 |
+
resolution: 256
|
| 49 |
+
in_channels: 3
|
| 50 |
+
out_ch: 3
|
| 51 |
+
ch: 128
|
| 52 |
+
ch_mult:
|
| 53 |
+
- 1
|
| 54 |
+
- 2
|
| 55 |
+
- 4
|
| 56 |
+
- 4
|
| 57 |
+
num_res_blocks: 2
|
| 58 |
+
attn_resolutions: [ ]
|
| 59 |
+
dropout: 0.0
|
| 60 |
+
lossconfig:
|
| 61 |
+
target: torch.nn.Identity
|
| 62 |
+
|
| 63 |
+
cond_stage_config:
|
| 64 |
+
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
| 65 |
+
params:
|
| 66 |
+
freeze: True
|
| 67 |
+
layer: "penultimate"
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
data:
|
| 71 |
+
target: ldm.data.laion.WebDataModuleFromConfig
|
| 72 |
+
params:
|
| 73 |
+
tar_base: null # for concat as in LAION-A
|
| 74 |
+
p_unsafe_threshold: 0.1
|
| 75 |
+
filter_word_list: "data/filters.yaml"
|
| 76 |
+
max_pwatermark: 0.45
|
| 77 |
+
batch_size: 8
|
| 78 |
+
num_workers: 6
|
| 79 |
+
multinode: True
|
| 80 |
+
min_size: 512
|
| 81 |
+
train:
|
| 82 |
+
shards:
|
| 83 |
+
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
|
| 84 |
+
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
|
| 85 |
+
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
|
| 86 |
+
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
|
| 87 |
+
- "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -" #{00000-94333}.tar"
|
| 88 |
+
shuffle: 10000
|
| 89 |
+
image_key: jpg
|
| 90 |
+
image_transforms:
|
| 91 |
+
- target: torchvision.transforms.Resize
|
| 92 |
+
params:
|
| 93 |
+
size: 512
|
| 94 |
+
interpolation: 3
|
| 95 |
+
- target: torchvision.transforms.RandomCrop
|
| 96 |
+
params:
|
| 97 |
+
size: 512
|
| 98 |
+
postprocess:
|
| 99 |
+
target: ldm.data.laion.AddMask
|
| 100 |
+
params:
|
| 101 |
+
mode: "512train-large"
|
| 102 |
+
p_drop: 0.25
|
| 103 |
+
# NOTE use enough shards to avoid empty validation loops in workers
|
| 104 |
+
validation:
|
| 105 |
+
shards:
|
| 106 |
+
- "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
|
| 107 |
+
shuffle: 0
|
| 108 |
+
image_key: jpg
|
| 109 |
+
image_transforms:
|
| 110 |
+
- target: torchvision.transforms.Resize
|
| 111 |
+
params:
|
| 112 |
+
size: 512
|
| 113 |
+
interpolation: 3
|
| 114 |
+
- target: torchvision.transforms.CenterCrop
|
| 115 |
+
params:
|
| 116 |
+
size: 512
|
| 117 |
+
postprocess:
|
| 118 |
+
target: ldm.data.laion.AddMask
|
| 119 |
+
params:
|
| 120 |
+
mode: "512train-large"
|
| 121 |
+
p_drop: 0.25
|
| 122 |
+
|
| 123 |
+
lightning:
|
| 124 |
+
find_unused_parameters: True
|
| 125 |
+
modelcheckpoint:
|
| 126 |
+
params:
|
| 127 |
+
every_n_train_steps: 5000
|
| 128 |
+
|
| 129 |
+
callbacks:
|
| 130 |
+
metrics_over_trainsteps_checkpoint:
|
| 131 |
+
params:
|
| 132 |
+
every_n_train_steps: 10000
|
| 133 |
+
|
| 134 |
+
image_logger:
|
| 135 |
+
target: main.ImageLogger
|
| 136 |
+
params:
|
| 137 |
+
enable_autocast: False
|
| 138 |
+
disabled: False
|
| 139 |
+
batch_frequency: 1000
|
| 140 |
+
max_images: 4
|
| 141 |
+
increase_log_steps: False
|
| 142 |
+
log_first_step: False
|
| 143 |
+
log_images_kwargs:
|
| 144 |
+
use_ema_scope: False
|
| 145 |
+
inpaint: False
|
| 146 |
+
plot_progressive_rows: False
|
| 147 |
+
plot_diffusion_rows: False
|
| 148 |
+
N: 4
|
| 149 |
+
unconditional_guidance_scale: 5.0
|
| 150 |
+
unconditional_guidance_label: [""]
|
| 151 |
+
ddim_steps: 50 # todo check these out for depth2img,
|
| 152 |
+
ddim_eta: 0.0 # todo check these out for depth2img,
|
| 153 |
+
|
| 154 |
+
trainer:
|
| 155 |
+
benchmark: True
|
| 156 |
+
val_check_interval: 5000000
|
| 157 |
+
num_sanity_val_steps: 0
|
| 158 |
+
accumulate_grad_batches: 1
|
controlnet/color_finetune.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b18346e9b3a153f3a292574d958538c93f77e217c05ab08bffc09f1081a2f54d
|
| 3 |
+
size 1445157120
|
controlnet/control_v11p_sd15_scribble.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:387ade970396c191da0fd229d26bbb64f80b8b3c501a774d9838e54638deccb1
|
| 3 |
+
size 1445157124
|
inpaint/brushnet/random_mask_brushnet_ckpt/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "BrushNetModel",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"_name_or_path": "runs/logs/brushnet_randommask/checkpoint-100000",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"brushnet_conditioning_channel_order": "rgb",
|
| 17 |
+
"class_embed_type": null,
|
| 18 |
+
"conditioning_channels": 5,
|
| 19 |
+
"conditioning_embedding_out_channels": [
|
| 20 |
+
16,
|
| 21 |
+
32,
|
| 22 |
+
96,
|
| 23 |
+
256
|
| 24 |
+
],
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"DownBlock2D",
|
| 28 |
+
"DownBlock2D",
|
| 29 |
+
"DownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "MidBlock2D",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"up_block_types": [
|
| 51 |
+
"UpBlock2D",
|
| 52 |
+
"UpBlock2D",
|
| 53 |
+
"UpBlock2D",
|
| 54 |
+
"UpBlock2D"
|
| 55 |
+
],
|
| 56 |
+
"upcast_attention": false,
|
| 57 |
+
"use_linear_projection": false
|
| 58 |
+
}
|
inpaint/brushnet/random_mask_brushnet_ckpt/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb94edf13c2284098a5cac01280d810abba53cf4e5f0d795ddc65ff36f0754e6
|
| 3 |
+
size 2475354520
|
inpaint/brushnet/segmentation_mask_brushnet_ckpt/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "BrushNetModel",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"_name_or_path": "runs/logs/brushnet_segmask/checkpoint-550000",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"brushnet_conditioning_channel_order": "rgb",
|
| 17 |
+
"class_embed_type": null,
|
| 18 |
+
"conditioning_channels": 5,
|
| 19 |
+
"conditioning_embedding_out_channels": [
|
| 20 |
+
16,
|
| 21 |
+
32,
|
| 22 |
+
96,
|
| 23 |
+
256
|
| 24 |
+
],
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"DownBlock2D",
|
| 28 |
+
"DownBlock2D",
|
| 29 |
+
"DownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "MidBlock2D",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"up_block_types": [
|
| 51 |
+
"UpBlock2D",
|
| 52 |
+
"UpBlock2D",
|
| 53 |
+
"UpBlock2D",
|
| 54 |
+
"UpBlock2D"
|
| 55 |
+
],
|
| 56 |
+
"upcast_attention": false,
|
| 57 |
+
"use_linear_projection": false
|
| 58 |
+
}
|
inpaint/brushnet/segmentation_mask_brushnet_ckpt/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02f9849340d41f9e27b16facd0c1debf1504aedb590f73638b1d3711e8deb61d
|
| 3 |
+
size 1669734400
|
llava-v1.5-7b-finetune-clean/config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "liuhaotian/llava-v1.5-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"freeze_mm_mlp_adapter": false,
|
| 11 |
+
"freeze_mm_vision_resampler": false,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"image_aspect_ratio": "pad",
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 11008,
|
| 17 |
+
"max_length": 4096,
|
| 18 |
+
"max_position_embeddings": 4096,
|
| 19 |
+
"mm_hidden_size": 1024,
|
| 20 |
+
"mm_patch_merge_type": "flat",
|
| 21 |
+
"mm_projector_lr": 2e-05,
|
| 22 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 23 |
+
"mm_resampler_type": null,
|
| 24 |
+
"mm_use_im_patch_token": false,
|
| 25 |
+
"mm_use_im_start_end": false,
|
| 26 |
+
"mm_vision_select_feature": "patch",
|
| 27 |
+
"mm_vision_select_layer": -2,
|
| 28 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 29 |
+
"model_type": "llava_llama",
|
| 30 |
+
"num_attention_heads": 32,
|
| 31 |
+
"num_hidden_layers": 32,
|
| 32 |
+
"num_key_value_heads": 32,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"pretraining_tp": 1,
|
| 35 |
+
"rms_norm_eps": 1e-05,
|
| 36 |
+
"rope_scaling": null,
|
| 37 |
+
"rope_theta": 10000.0,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"tokenizer_model_max_length": 2048,
|
| 40 |
+
"tokenizer_padding_side": "right",
|
| 41 |
+
"torch_dtype": "float16",
|
| 42 |
+
"transformers_version": "4.37.2",
|
| 43 |
+
"tune_mm_mlp_adapter": false,
|
| 44 |
+
"tune_mm_vision_resampler": false,
|
| 45 |
+
"unfreeze_mm_vision_tower": false,
|
| 46 |
+
"use_cache": false,
|
| 47 |
+
"use_mm_proj": true,
|
| 48 |
+
"vocab_size": 32000
|
| 49 |
+
}
|
llava-v1.5-7b-finetune-clean/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 4096,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.37.2"
|
| 7 |
+
}
|
llava-v1.5-7b-finetune-clean/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa70cff1948a6d2a37c454b317628ea03cdb6d431ea6d93607f5c521bc34b31c
|
| 3 |
+
size 4938985248
|
llava-v1.5-7b-finetune-clean/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02bd0cca1575553d2dacc51db0f1307313e96575c24abb559897a2a264b19d74
|
| 3 |
+
size 4947390768
|
llava-v1.5-7b-finetune-clean/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39f1c9c21594bf3dd37d0f918c2c47f942a0b3a4b7ccb5916f5e84175c51b2ac
|
| 3 |
+
size 4239524472
|
llava-v1.5-7b-finetune-clean/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,693 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14125805568
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.mm_projector.0.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.mm_projector.0.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.mm_projector.2.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.mm_projector.2.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.norm.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00003.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00003.safetensors"
|
| 692 |
+
}
|
| 693 |
+
}
|
llava-v1.5-7b-finetune-clean/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
llava-v1.5-7b-finetune-clean/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llava-v1.5-7b-finetune-clean/tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|
preprocessor/sk_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c686ced2a666b4850b4bb6ccf0748031c3eda9f822de73a34b8979970d90f0c6
|
| 3 |
+
size 17173511
|
preprocessor/sk_model2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a534781061f34e83bb9406b4335da4ff2616c95d22a585c1245aa8363e74e0
|
| 3 |
+
size 17173511
|