Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- sft/run04_3sys_frozen/private/assets/config.yaml +123 -0
- sft/run04_3sys_frozen/private/assets/config.yaml.before-input-mode-20260911T063731Z.bak +122 -0
- sft/run04_3sys_frozen/private/assets/reason1/chat_template.json +3 -0
- sft/run04_3sys_frozen/private/assets/reason1/config.json +61 -0
- sft/run04_3sys_frozen/private/assets/reason1/generation_config.json +12 -0
- sft/run04_3sys_frozen/private/assets/reason1/preprocessor_config.json +19 -0
- sft/run04_3sys_frozen/private/assets/reason1/tokenizer_config.json +207 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/chat_template.json +4 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/config.json +63 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/generation_config.json +14 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/merges.txt +0 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/preprocessor_config.json +21 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/tokenizer.json +0 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/tokenizer_config.json +239 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/video_preprocessor_config.json +21 -0
- sft/run04_3sys_frozen/private/assets/vlm_expert/vocab.json +0 -0
- sft/run10_3sys/private/assets/config.yaml +149 -0
- sft/run10_3sys/private/assets/config.yaml.before-input-mode-20260911T063731Z.bak +148 -0
- sft/run10_3sys/private/assets/reason1/chat_template.json +3 -0
- sft/run10_3sys/private/assets/reason1/config.json +61 -0
- sft/run10_3sys/private/assets/reason1/generation_config.json +12 -0
- sft/run10_3sys/private/assets/reason1/preprocessor_config.json +19 -0
- sft/run10_3sys/private/assets/reason1/tokenizer.json +0 -0
- sft/run10_3sys/private/assets/reason1/tokenizer_config.json +207 -0
- sft/run10_3sys/private/assets/vlm_expert/chat_template.json +4 -0
- sft/run10_3sys/private/assets/vlm_expert/config.json +63 -0
- sft/run10_3sys/private/assets/vlm_expert/generation_config.json +14 -0
- sft/run10_3sys/private/assets/vlm_expert/merges.txt +0 -0
- sft/run10_3sys/private/assets/vlm_expert/preprocessor_config.json +21 -0
- sft/run10_3sys/private/assets/vlm_expert/tokenizer.json +0 -0
- sft/run10_3sys/private/assets/vlm_expert/tokenizer_config.json +239 -0
- sft/run10_3sys/private/assets/vlm_expert/video_preprocessor_config.json +21 -0
- sft/run10_3sys/private/assets/vlm_expert/vocab.json +0 -0
- sft/run11_2sys_scratch_dinov3/private/assets/config.yaml +148 -0
- sft/run11_2sys_scratch_dinov3/private/assets/dinov3/config.json +32 -0
- sft/run11_2sys_scratch_dinov3/private/assets/reason1/chat_template.json +3 -0
- sft/run11_2sys_scratch_dinov3/private/assets/reason1/config.json +61 -0
- sft/run11_2sys_scratch_dinov3/private/assets/reason1/generation_config.json +12 -0
- sft/run11_2sys_scratch_dinov3/private/assets/reason1/preprocessor_config.json +19 -0
- sft/run11_2sys_scratch_dinov3/private/assets/reason1/tokenizer.json +0 -0
- sft/run11_2sys_scratch_dinov3/private/assets/reason1/tokenizer_config.json +207 -0
- sft/run11_2sys_scratch_dinov3/private/assets/svae_config.json +1 -0
- sft/run20_3sys_vlm_dino/private/assets/config.yaml +168 -0
- sft/run20_3sys_vlm_dino/private/assets/reason1/chat_template.json +3 -0
- sft/run20_3sys_vlm_dino/private/assets/reason1/config.json +61 -0
- sft/run20_3sys_vlm_dino/private/assets/reason1/generation_config.json +12 -0
- sft/run20_3sys_vlm_dino/private/assets/reason1/preprocessor_config.json +19 -0
- sft/run20_3sys_vlm_dino/private/assets/reason1/tokenizer.json +0 -0
- sft/run20_3sys_vlm_dino/private/assets/reason1/tokenizer_config.json +207 -0
- sft/run20_3sys_vlm_dino/private/assets/vlm_expert/chat_template.json +4 -0
sft/run04_3sys_frozen/private/assets/config.yaml
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
video_backbone:
|
| 3 |
+
name: cosmos_predict25_2b
|
| 4 |
+
model_path: /mnt/data/limingleyang/model/Cosmos-Predict2.5-2B
|
| 5 |
+
model_variant: base/post-trained
|
| 6 |
+
text_encoder_path: /mnt/data/limingleyang/model/Cosmos-Reason1-7B
|
| 7 |
+
text_encoder_dropout: 0.0
|
| 8 |
+
vae: wan2pt1
|
| 9 |
+
shift_video: 5.0
|
| 10 |
+
components:
|
| 11 |
+
- attr: vae
|
| 12 |
+
source: state_dict
|
| 13 |
+
sub_module: vae
|
| 14 |
+
- attr: text_encoder
|
| 15 |
+
source: state_dict
|
| 16 |
+
sub_module: reason1
|
| 17 |
+
action_backbone:
|
| 18 |
+
dim: 1024
|
| 19 |
+
ffn_dim: 4096
|
| 20 |
+
shift_action: 5.0
|
| 21 |
+
vlm_expert:
|
| 22 |
+
input_mode: legacy_stitched
|
| 23 |
+
checkpoint_path: /mnt/data/limingleyang/model/Qwen3-VL-2B-Instruct
|
| 24 |
+
load_pretrained: true
|
| 25 |
+
max_length: 512
|
| 26 |
+
freeze_vision_tower: true
|
| 27 |
+
freeze_embed_tokens: true
|
| 28 |
+
freeze_decoder_layers: true
|
| 29 |
+
run_full_tail: false
|
| 30 |
+
use_gradient_checkpointing: false
|
| 31 |
+
freeze:
|
| 32 |
+
- video_backbone.text_encoder
|
| 33 |
+
- video_backbone.reason1
|
| 34 |
+
- video_backbone.vae
|
| 35 |
+
- video_backbone.image_encoder
|
| 36 |
+
- video_backbone.video_encoder
|
| 37 |
+
architecture:
|
| 38 |
+
framework: tri_system
|
| 39 |
+
variant: joint_self_attn
|
| 40 |
+
action_dim: 80
|
| 41 |
+
use_proprioception: true
|
| 42 |
+
state_dim: 80
|
| 43 |
+
attention_mask_mode: mutual
|
| 44 |
+
video_attention_mask_mode: first_frame_causal
|
| 45 |
+
vlm_attn_warmup:
|
| 46 |
+
start_weight: 1.0
|
| 47 |
+
end_weight: 1.0
|
| 48 |
+
delay_ratio: 0.0
|
| 49 |
+
ramp_ratio: 0.0
|
| 50 |
+
shape: linear
|
| 51 |
+
mot_checkpoint_mixed_attn: false
|
| 52 |
+
bridge_layers: null
|
| 53 |
+
bridge_interval: 1
|
| 54 |
+
dataloader:
|
| 55 |
+
type: libero
|
| 56 |
+
dataset_dir: /mnt/data/wangyuran/benchmark_data/libero
|
| 57 |
+
action_mode: libero
|
| 58 |
+
gripper_convention: minus1_closed_plus1_open
|
| 59 |
+
unify_action: true
|
| 60 |
+
unify_action_map:
|
| 61 |
+
- 0-9
|
| 62 |
+
normalize_mode: min-max
|
| 63 |
+
head_camera_priority:
|
| 64 |
+
- observation.images.image
|
| 65 |
+
wrist_camera_priority:
|
| 66 |
+
- observation.images.wrist_image
|
| 67 |
+
- observation.images.image2
|
| 68 |
+
prompt_columns:
|
| 69 |
+
- language_instruction
|
| 70 |
+
- task
|
| 71 |
+
- prompt
|
| 72 |
+
num_frames: 33
|
| 73 |
+
video_stride: 4
|
| 74 |
+
window_stride: 1
|
| 75 |
+
height: 384
|
| 76 |
+
width: 320
|
| 77 |
+
multiview: true
|
| 78 |
+
split: train
|
| 79 |
+
enable_action_supervision: true
|
| 80 |
+
seed: 42
|
| 81 |
+
training:
|
| 82 |
+
debug: false
|
| 83 |
+
learning_rate: 0.0001
|
| 84 |
+
adam_betas:
|
| 85 |
+
- 0.9
|
| 86 |
+
- 0.95
|
| 87 |
+
weight_decay: 0.01
|
| 88 |
+
max_grad_norm: 1.0
|
| 89 |
+
num_epochs: 10
|
| 90 |
+
max_steps: null
|
| 91 |
+
batch_size: 4
|
| 92 |
+
gradient_accumulation_steps: 1
|
| 93 |
+
lr_scheduler: cosine
|
| 94 |
+
warmup_ratio: 0.05
|
| 95 |
+
lr_min_ratio: 0.01
|
| 96 |
+
vlm_warmup_ratio: null
|
| 97 |
+
action_lr: null
|
| 98 |
+
video_lr: null
|
| 99 |
+
vlm_lr: null
|
| 100 |
+
mixed_precision: bf16
|
| 101 |
+
zero_stage: 2
|
| 102 |
+
use_gradient_checkpointing: false
|
| 103 |
+
use_gradient_checkpointing_offload: false
|
| 104 |
+
initialize_model_on_cpu: false
|
| 105 |
+
offload_optimizer_device: none
|
| 106 |
+
lambda_video: 1.0
|
| 107 |
+
lambda_action: 1.0
|
| 108 |
+
max_timestep_boundary: 1.0
|
| 109 |
+
min_timestep_boundary: 0.0
|
| 110 |
+
output_path: /mnt/data/limingleyang/openwam_checkpoints
|
| 111 |
+
save_steps: 2000
|
| 112 |
+
keep_last_k_ckpts: 1
|
| 113 |
+
finetune_ckpt_path: null
|
| 114 |
+
resume_ckpt_path: null
|
| 115 |
+
dataset_num_workers: 8
|
| 116 |
+
project:
|
| 117 |
+
name: open-wam
|
| 118 |
+
output_dir: outputs/${now:%Y-%m-%d_%H-%M-%S}
|
| 119 |
+
seed: 42
|
| 120 |
+
wandb:
|
| 121 |
+
project: open-wam
|
| 122 |
+
run_name: null
|
| 123 |
+
entity: null
|
sft/run04_3sys_frozen/private/assets/config.yaml.before-input-mode-20260911T063731Z.bak
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
video_backbone:
|
| 3 |
+
name: cosmos_predict25_2b
|
| 4 |
+
model_path: /mnt/data/limingleyang/model/Cosmos-Predict2.5-2B
|
| 5 |
+
model_variant: base/post-trained
|
| 6 |
+
text_encoder_path: /mnt/data/limingleyang/model/Cosmos-Reason1-7B
|
| 7 |
+
text_encoder_dropout: 0.0
|
| 8 |
+
vae: wan2pt1
|
| 9 |
+
shift_video: 5.0
|
| 10 |
+
components:
|
| 11 |
+
- attr: vae
|
| 12 |
+
source: state_dict
|
| 13 |
+
sub_module: vae
|
| 14 |
+
- attr: text_encoder
|
| 15 |
+
source: state_dict
|
| 16 |
+
sub_module: reason1
|
| 17 |
+
action_backbone:
|
| 18 |
+
dim: 1024
|
| 19 |
+
ffn_dim: 4096
|
| 20 |
+
shift_action: 5.0
|
| 21 |
+
vlm_expert:
|
| 22 |
+
checkpoint_path: /mnt/data/limingleyang/model/Qwen3-VL-2B-Instruct
|
| 23 |
+
load_pretrained: true
|
| 24 |
+
max_length: 512
|
| 25 |
+
freeze_vision_tower: true
|
| 26 |
+
freeze_embed_tokens: true
|
| 27 |
+
freeze_decoder_layers: true
|
| 28 |
+
run_full_tail: false
|
| 29 |
+
use_gradient_checkpointing: false
|
| 30 |
+
freeze:
|
| 31 |
+
- video_backbone.text_encoder
|
| 32 |
+
- video_backbone.reason1
|
| 33 |
+
- video_backbone.vae
|
| 34 |
+
- video_backbone.image_encoder
|
| 35 |
+
- video_backbone.video_encoder
|
| 36 |
+
architecture:
|
| 37 |
+
framework: tri_system
|
| 38 |
+
variant: joint_self_attn
|
| 39 |
+
action_dim: 80
|
| 40 |
+
use_proprioception: true
|
| 41 |
+
state_dim: 80
|
| 42 |
+
attention_mask_mode: mutual
|
| 43 |
+
video_attention_mask_mode: first_frame_causal
|
| 44 |
+
vlm_attn_warmup:
|
| 45 |
+
start_weight: 1.0
|
| 46 |
+
end_weight: 1.0
|
| 47 |
+
delay_ratio: 0.0
|
| 48 |
+
ramp_ratio: 0.0
|
| 49 |
+
shape: linear
|
| 50 |
+
mot_checkpoint_mixed_attn: false
|
| 51 |
+
bridge_layers: null
|
| 52 |
+
bridge_interval: 1
|
| 53 |
+
dataloader:
|
| 54 |
+
type: libero
|
| 55 |
+
dataset_dir: /mnt/data/wangyuran/benchmark_data/libero
|
| 56 |
+
action_mode: libero
|
| 57 |
+
gripper_convention: minus1_closed_plus1_open
|
| 58 |
+
unify_action: true
|
| 59 |
+
unify_action_map:
|
| 60 |
+
- 0-9
|
| 61 |
+
normalize_mode: min-max
|
| 62 |
+
head_camera_priority:
|
| 63 |
+
- observation.images.image
|
| 64 |
+
wrist_camera_priority:
|
| 65 |
+
- observation.images.wrist_image
|
| 66 |
+
- observation.images.image2
|
| 67 |
+
prompt_columns:
|
| 68 |
+
- language_instruction
|
| 69 |
+
- task
|
| 70 |
+
- prompt
|
| 71 |
+
num_frames: 33
|
| 72 |
+
video_stride: 4
|
| 73 |
+
window_stride: 1
|
| 74 |
+
height: 384
|
| 75 |
+
width: 320
|
| 76 |
+
multiview: true
|
| 77 |
+
split: train
|
| 78 |
+
enable_action_supervision: true
|
| 79 |
+
seed: 42
|
| 80 |
+
training:
|
| 81 |
+
debug: false
|
| 82 |
+
learning_rate: 0.0001
|
| 83 |
+
adam_betas:
|
| 84 |
+
- 0.9
|
| 85 |
+
- 0.95
|
| 86 |
+
weight_decay: 0.01
|
| 87 |
+
max_grad_norm: 1.0
|
| 88 |
+
num_epochs: 10
|
| 89 |
+
max_steps: null
|
| 90 |
+
batch_size: 4
|
| 91 |
+
gradient_accumulation_steps: 1
|
| 92 |
+
lr_scheduler: cosine
|
| 93 |
+
warmup_ratio: 0.05
|
| 94 |
+
lr_min_ratio: 0.01
|
| 95 |
+
vlm_warmup_ratio: null
|
| 96 |
+
action_lr: null
|
| 97 |
+
video_lr: null
|
| 98 |
+
vlm_lr: null
|
| 99 |
+
mixed_precision: bf16
|
| 100 |
+
zero_stage: 2
|
| 101 |
+
use_gradient_checkpointing: false
|
| 102 |
+
use_gradient_checkpointing_offload: false
|
| 103 |
+
initialize_model_on_cpu: false
|
| 104 |
+
offload_optimizer_device: none
|
| 105 |
+
lambda_video: 1.0
|
| 106 |
+
lambda_action: 1.0
|
| 107 |
+
max_timestep_boundary: 1.0
|
| 108 |
+
min_timestep_boundary: 0.0
|
| 109 |
+
output_path: /mnt/data/limingleyang/openwam_checkpoints
|
| 110 |
+
save_steps: 2000
|
| 111 |
+
keep_last_k_ckpts: 1
|
| 112 |
+
finetune_ckpt_path: null
|
| 113 |
+
resume_ckpt_path: null
|
| 114 |
+
dataset_num_workers: 8
|
| 115 |
+
project:
|
| 116 |
+
name: open-wam
|
| 117 |
+
output_dir: outputs/${now:%Y-%m-%d_%H-%M-%S}
|
| 118 |
+
seed: 42
|
| 119 |
+
wandb:
|
| 120 |
+
project: open-wam
|
| 121 |
+
run_name: null
|
| 122 |
+
entity: null
|
sft/run04_3sys_frozen/private/assets/reason1/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
sft/run04_3sys_frozen/private/assets/reason1/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 32768,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 1280,
|
| 35 |
+
"intermediate_size": 3420,
|
| 36 |
+
"num_heads": 16,
|
| 37 |
+
"in_chans": 3,
|
| 38 |
+
"out_hidden_size": 3584,
|
| 39 |
+
"patch_size": 14,
|
| 40 |
+
"spatial_merge_size": 2,
|
| 41 |
+
"spatial_patch_size": 14,
|
| 42 |
+
"window_size": 112,
|
| 43 |
+
"fullatt_block_indexes": [
|
| 44 |
+
7,
|
| 45 |
+
15,
|
| 46 |
+
23,
|
| 47 |
+
31
|
| 48 |
+
],
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"temporal_patch_size": 2
|
| 51 |
+
},
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"type": "mrope",
|
| 54 |
+
"mrope_section": [
|
| 55 |
+
16,
|
| 56 |
+
24,
|
| 57 |
+
24
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
"vocab_size": 152064
|
| 61 |
+
}
|
sft/run04_3sys_frozen/private/assets/reason1/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.000001,
|
| 11 |
+
"transformers_version": "4.37.0"
|
| 12 |
+
}
|
sft/run04_3sys_frozen/private/assets/reason1/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
sft/run04_3sys_frozen/private/assets/reason1/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"additional_special_tokens": [
|
| 182 |
+
"<|im_start|>",
|
| 183 |
+
"<|im_end|>",
|
| 184 |
+
"<|object_ref_start|>",
|
| 185 |
+
"<|object_ref_end|>",
|
| 186 |
+
"<|box_start|>",
|
| 187 |
+
"<|box_end|>",
|
| 188 |
+
"<|quad_start|>",
|
| 189 |
+
"<|quad_end|>",
|
| 190 |
+
"<|vision_start|>",
|
| 191 |
+
"<|vision_end|>",
|
| 192 |
+
"<|vision_pad|>",
|
| 193 |
+
"<|image_pad|>",
|
| 194 |
+
"<|video_pad|>"
|
| 195 |
+
],
|
| 196 |
+
"bos_token": null,
|
| 197 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"model_max_length": 131072,
|
| 202 |
+
"pad_token": "<|endoftext|>",
|
| 203 |
+
"split_special_tokens": false,
|
| 204 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 205 |
+
"unk_token": null,
|
| 206 |
+
"add_bos_token": false
|
| 207 |
+
}
|
sft/run04_3sys_frozen/private/assets/vlm_expert/chat_template.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
| 4 |
+
|
sft/run04_3sys_frozen/private/assets/vlm_expert/config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 151655,
|
| 6 |
+
"model_type": "qwen3_vl",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 151645,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 6144,
|
| 18 |
+
"max_position_embeddings": 262144,
|
| 19 |
+
"model_type": "qwen3_vl_text",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"mrope_interleaved": true,
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
24,
|
| 28 |
+
20,
|
| 29 |
+
20
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 5000000,
|
| 34 |
+
"tie_word_embeddings": true,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 151936
|
| 37 |
+
},
|
| 38 |
+
"tie_word_embeddings": true,
|
| 39 |
+
"transformers_version": "4.57.0.dev0",
|
| 40 |
+
"video_token_id": 151656,
|
| 41 |
+
"vision_config": {
|
| 42 |
+
"deepstack_visual_indexes": [
|
| 43 |
+
5,
|
| 44 |
+
11,
|
| 45 |
+
17
|
| 46 |
+
],
|
| 47 |
+
"depth": 24,
|
| 48 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 49 |
+
"hidden_size": 1024,
|
| 50 |
+
"in_channels": 3,
|
| 51 |
+
"initializer_range": 0.02,
|
| 52 |
+
"intermediate_size": 4096,
|
| 53 |
+
"model_type": "qwen3_vl",
|
| 54 |
+
"num_heads": 16,
|
| 55 |
+
"num_position_embeddings": 2304,
|
| 56 |
+
"out_hidden_size": 2048,
|
| 57 |
+
"patch_size": 16,
|
| 58 |
+
"spatial_merge_size": 2,
|
| 59 |
+
"temporal_patch_size": 2
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652
|
| 63 |
+
}
|
sft/run04_3sys_frozen/private/assets/vlm_expert/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_p": 0.8,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"repetition_penalty": 1.0,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
sft/run04_3sys_frozen/private/assets/vlm_expert/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run04_3sys_frozen/private/assets/vlm_expert/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
sft/run04_3sys_frozen/private/assets/vlm_expert/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run04_3sys_frozen/private/assets/vlm_expert/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
sft/run04_3sys_frozen/private/assets/vlm_expert/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
sft/run04_3sys_frozen/private/assets/vlm_expert/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run10_3sys/private/assets/config.yaml
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
video_backbone:
|
| 3 |
+
name: cosmos_predict25_2b
|
| 4 |
+
model_path: /mnt/data/limingleyang/model/Cosmos-Predict2.5-2B
|
| 5 |
+
model_variant: base/post-trained
|
| 6 |
+
text_encoder_path: /mnt/data/limingleyang/model/Cosmos-Reason1-7B
|
| 7 |
+
text_encoder_dropout: 0.0
|
| 8 |
+
vae: wan2pt1
|
| 9 |
+
shift_video: 5.0
|
| 10 |
+
dit_config:
|
| 11 |
+
max_img_h: 240
|
| 12 |
+
max_img_w: 240
|
| 13 |
+
max_frames: 128
|
| 14 |
+
in_channels: 16
|
| 15 |
+
out_channels: 16
|
| 16 |
+
patch_spatial: 2
|
| 17 |
+
patch_temporal: 1
|
| 18 |
+
model_channels: 2048
|
| 19 |
+
num_blocks: 28
|
| 20 |
+
num_heads: 16
|
| 21 |
+
concat_padding_mask: true
|
| 22 |
+
crossattn_emb_channels: 1024
|
| 23 |
+
use_crossattn_projection: true
|
| 24 |
+
crossattn_proj_in_channels: 100352
|
| 25 |
+
pos_emb_cls: rope3d
|
| 26 |
+
pos_emb_learnable: true
|
| 27 |
+
pos_emb_interpolation: crop
|
| 28 |
+
use_adaln_lora: true
|
| 29 |
+
adaln_lora_dim: 256
|
| 30 |
+
atten_backend: transformer_engine
|
| 31 |
+
extra_per_block_abs_pos_emb: false
|
| 32 |
+
rope_h_extrapolation_ratio: 3.0
|
| 33 |
+
rope_w_extrapolation_ratio: 3.0
|
| 34 |
+
rope_t_extrapolation_ratio: 1.0
|
| 35 |
+
rope_enable_fps_modulation: false
|
| 36 |
+
components:
|
| 37 |
+
- attr: vae
|
| 38 |
+
source: state_dict
|
| 39 |
+
sub_module: vae
|
| 40 |
+
- attr: text_encoder
|
| 41 |
+
source: state_dict
|
| 42 |
+
sub_module: reason1
|
| 43 |
+
action_backbone:
|
| 44 |
+
dim: 1024
|
| 45 |
+
ffn_dim: 4096
|
| 46 |
+
shift_action: 5.0
|
| 47 |
+
vlm_expert:
|
| 48 |
+
input_mode: legacy_stitched
|
| 49 |
+
checkpoint_path: /mnt/data/limingleyang/model/Qwen3-VL-2B-Instruct
|
| 50 |
+
load_pretrained: true
|
| 51 |
+
max_length: 512
|
| 52 |
+
freeze_vision_tower: true
|
| 53 |
+
freeze_embed_tokens: true
|
| 54 |
+
freeze_decoder_layers: false
|
| 55 |
+
run_full_tail: false
|
| 56 |
+
use_gradient_checkpointing: false
|
| 57 |
+
freeze:
|
| 58 |
+
- video_backbone.text_encoder
|
| 59 |
+
- video_backbone.reason1
|
| 60 |
+
- video_backbone.vae
|
| 61 |
+
- video_backbone.image_encoder
|
| 62 |
+
- video_backbone.video_encoder
|
| 63 |
+
architecture:
|
| 64 |
+
framework: tri_system
|
| 65 |
+
variant: joint_self_attn
|
| 66 |
+
action_dim: 80
|
| 67 |
+
use_proprioception: true
|
| 68 |
+
state_dim: 80
|
| 69 |
+
attention_mask_mode: mutual
|
| 70 |
+
video_attention_mask_mode: first_frame_causal
|
| 71 |
+
vlm_attn_warmup:
|
| 72 |
+
start_weight: 0.01
|
| 73 |
+
end_weight: 1.0
|
| 74 |
+
delay_ratio: 0.0
|
| 75 |
+
ramp_ratio: 0.4
|
| 76 |
+
shape: linear
|
| 77 |
+
mot_checkpoint_mixed_attn: false
|
| 78 |
+
bridge_layers: null
|
| 79 |
+
bridge_interval: 1
|
| 80 |
+
dataloader:
|
| 81 |
+
type: libero
|
| 82 |
+
dataset_dir: /mnt/data/wangyuran/benchmark_data/libero
|
| 83 |
+
action_mode: libero
|
| 84 |
+
gripper_convention: minus1_closed_plus1_open
|
| 85 |
+
unify_action: true
|
| 86 |
+
unify_action_map:
|
| 87 |
+
- 0-9
|
| 88 |
+
normalize_mode: min-max
|
| 89 |
+
head_camera_priority:
|
| 90 |
+
- observation.images.image
|
| 91 |
+
wrist_camera_priority:
|
| 92 |
+
- observation.images.wrist_image
|
| 93 |
+
- observation.images.image2
|
| 94 |
+
prompt_columns:
|
| 95 |
+
- language_instruction
|
| 96 |
+
- task
|
| 97 |
+
- prompt
|
| 98 |
+
num_frames: 33
|
| 99 |
+
video_stride: 4
|
| 100 |
+
window_stride: 1
|
| 101 |
+
height: 384
|
| 102 |
+
width: 320
|
| 103 |
+
multiview: true
|
| 104 |
+
split: train
|
| 105 |
+
enable_action_supervision: true
|
| 106 |
+
seed: 42
|
| 107 |
+
training:
|
| 108 |
+
debug: false
|
| 109 |
+
learning_rate: 0.0001
|
| 110 |
+
adam_betas:
|
| 111 |
+
- 0.9
|
| 112 |
+
- 0.95
|
| 113 |
+
weight_decay: 0.01
|
| 114 |
+
max_grad_norm: 1.0
|
| 115 |
+
num_epochs: 10
|
| 116 |
+
max_steps: null
|
| 117 |
+
batch_size: 8
|
| 118 |
+
gradient_accumulation_steps: 1
|
| 119 |
+
lr_scheduler: cosine
|
| 120 |
+
warmup_ratio: 0.05
|
| 121 |
+
lr_min_ratio: 0.01
|
| 122 |
+
vlm_warmup_ratio: 0.1
|
| 123 |
+
action_lr: null
|
| 124 |
+
video_lr: null
|
| 125 |
+
vlm_lr: 1.0e-05
|
| 126 |
+
mixed_precision: bf16
|
| 127 |
+
zero_stage: 2
|
| 128 |
+
use_gradient_checkpointing: false
|
| 129 |
+
use_gradient_checkpointing_offload: false
|
| 130 |
+
initialize_model_on_cpu: false
|
| 131 |
+
offload_optimizer_device: none
|
| 132 |
+
lambda_video: 1.0
|
| 133 |
+
lambda_action: 1.0
|
| 134 |
+
max_timestep_boundary: 1.0
|
| 135 |
+
min_timestep_boundary: 0.0
|
| 136 |
+
output_path: /mnt/data/limingleyang/openwam_checkpoints
|
| 137 |
+
save_steps: 2000
|
| 138 |
+
keep_last_k_ckpts: 1
|
| 139 |
+
finetune_ckpt_path: null
|
| 140 |
+
resume_ckpt_path: null
|
| 141 |
+
dataset_num_workers: 8
|
| 142 |
+
project:
|
| 143 |
+
name: open-wam
|
| 144 |
+
output_dir: outputs/${now:%Y-%m-%d_%H-%M-%S}
|
| 145 |
+
seed: 42
|
| 146 |
+
wandb:
|
| 147 |
+
project: open-wam
|
| 148 |
+
run_name: null
|
| 149 |
+
entity: null
|
sft/run10_3sys/private/assets/config.yaml.before-input-mode-20260911T063731Z.bak
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
video_backbone:
|
| 3 |
+
name: cosmos_predict25_2b
|
| 4 |
+
model_path: /mnt/data/limingleyang/model/Cosmos-Predict2.5-2B
|
| 5 |
+
model_variant: base/post-trained
|
| 6 |
+
text_encoder_path: /mnt/data/limingleyang/model/Cosmos-Reason1-7B
|
| 7 |
+
text_encoder_dropout: 0.0
|
| 8 |
+
vae: wan2pt1
|
| 9 |
+
shift_video: 5.0
|
| 10 |
+
dit_config:
|
| 11 |
+
max_img_h: 240
|
| 12 |
+
max_img_w: 240
|
| 13 |
+
max_frames: 128
|
| 14 |
+
in_channels: 16
|
| 15 |
+
out_channels: 16
|
| 16 |
+
patch_spatial: 2
|
| 17 |
+
patch_temporal: 1
|
| 18 |
+
model_channels: 2048
|
| 19 |
+
num_blocks: 28
|
| 20 |
+
num_heads: 16
|
| 21 |
+
concat_padding_mask: true
|
| 22 |
+
crossattn_emb_channels: 1024
|
| 23 |
+
use_crossattn_projection: true
|
| 24 |
+
crossattn_proj_in_channels: 100352
|
| 25 |
+
pos_emb_cls: rope3d
|
| 26 |
+
pos_emb_learnable: true
|
| 27 |
+
pos_emb_interpolation: crop
|
| 28 |
+
use_adaln_lora: true
|
| 29 |
+
adaln_lora_dim: 256
|
| 30 |
+
atten_backend: transformer_engine
|
| 31 |
+
extra_per_block_abs_pos_emb: false
|
| 32 |
+
rope_h_extrapolation_ratio: 3.0
|
| 33 |
+
rope_w_extrapolation_ratio: 3.0
|
| 34 |
+
rope_t_extrapolation_ratio: 1.0
|
| 35 |
+
rope_enable_fps_modulation: false
|
| 36 |
+
components:
|
| 37 |
+
- attr: vae
|
| 38 |
+
source: state_dict
|
| 39 |
+
sub_module: vae
|
| 40 |
+
- attr: text_encoder
|
| 41 |
+
source: state_dict
|
| 42 |
+
sub_module: reason1
|
| 43 |
+
action_backbone:
|
| 44 |
+
dim: 1024
|
| 45 |
+
ffn_dim: 4096
|
| 46 |
+
shift_action: 5.0
|
| 47 |
+
vlm_expert:
|
| 48 |
+
checkpoint_path: /mnt/data/limingleyang/model/Qwen3-VL-2B-Instruct
|
| 49 |
+
load_pretrained: true
|
| 50 |
+
max_length: 512
|
| 51 |
+
freeze_vision_tower: true
|
| 52 |
+
freeze_embed_tokens: true
|
| 53 |
+
freeze_decoder_layers: false
|
| 54 |
+
run_full_tail: false
|
| 55 |
+
use_gradient_checkpointing: false
|
| 56 |
+
freeze:
|
| 57 |
+
- video_backbone.text_encoder
|
| 58 |
+
- video_backbone.reason1
|
| 59 |
+
- video_backbone.vae
|
| 60 |
+
- video_backbone.image_encoder
|
| 61 |
+
- video_backbone.video_encoder
|
| 62 |
+
architecture:
|
| 63 |
+
framework: tri_system
|
| 64 |
+
variant: joint_self_attn
|
| 65 |
+
action_dim: 80
|
| 66 |
+
use_proprioception: true
|
| 67 |
+
state_dim: 80
|
| 68 |
+
attention_mask_mode: mutual
|
| 69 |
+
video_attention_mask_mode: first_frame_causal
|
| 70 |
+
vlm_attn_warmup:
|
| 71 |
+
start_weight: 0.01
|
| 72 |
+
end_weight: 1.0
|
| 73 |
+
delay_ratio: 0.0
|
| 74 |
+
ramp_ratio: 0.4
|
| 75 |
+
shape: linear
|
| 76 |
+
mot_checkpoint_mixed_attn: false
|
| 77 |
+
bridge_layers: null
|
| 78 |
+
bridge_interval: 1
|
| 79 |
+
dataloader:
|
| 80 |
+
type: libero
|
| 81 |
+
dataset_dir: /mnt/data/wangyuran/benchmark_data/libero
|
| 82 |
+
action_mode: libero
|
| 83 |
+
gripper_convention: minus1_closed_plus1_open
|
| 84 |
+
unify_action: true
|
| 85 |
+
unify_action_map:
|
| 86 |
+
- 0-9
|
| 87 |
+
normalize_mode: min-max
|
| 88 |
+
head_camera_priority:
|
| 89 |
+
- observation.images.image
|
| 90 |
+
wrist_camera_priority:
|
| 91 |
+
- observation.images.wrist_image
|
| 92 |
+
- observation.images.image2
|
| 93 |
+
prompt_columns:
|
| 94 |
+
- language_instruction
|
| 95 |
+
- task
|
| 96 |
+
- prompt
|
| 97 |
+
num_frames: 33
|
| 98 |
+
video_stride: 4
|
| 99 |
+
window_stride: 1
|
| 100 |
+
height: 384
|
| 101 |
+
width: 320
|
| 102 |
+
multiview: true
|
| 103 |
+
split: train
|
| 104 |
+
enable_action_supervision: true
|
| 105 |
+
seed: 42
|
| 106 |
+
training:
|
| 107 |
+
debug: false
|
| 108 |
+
learning_rate: 0.0001
|
| 109 |
+
adam_betas:
|
| 110 |
+
- 0.9
|
| 111 |
+
- 0.95
|
| 112 |
+
weight_decay: 0.01
|
| 113 |
+
max_grad_norm: 1.0
|
| 114 |
+
num_epochs: 10
|
| 115 |
+
max_steps: null
|
| 116 |
+
batch_size: 8
|
| 117 |
+
gradient_accumulation_steps: 1
|
| 118 |
+
lr_scheduler: cosine
|
| 119 |
+
warmup_ratio: 0.05
|
| 120 |
+
lr_min_ratio: 0.01
|
| 121 |
+
vlm_warmup_ratio: 0.1
|
| 122 |
+
action_lr: null
|
| 123 |
+
video_lr: null
|
| 124 |
+
vlm_lr: 1.0e-05
|
| 125 |
+
mixed_precision: bf16
|
| 126 |
+
zero_stage: 2
|
| 127 |
+
use_gradient_checkpointing: false
|
| 128 |
+
use_gradient_checkpointing_offload: false
|
| 129 |
+
initialize_model_on_cpu: false
|
| 130 |
+
offload_optimizer_device: none
|
| 131 |
+
lambda_video: 1.0
|
| 132 |
+
lambda_action: 1.0
|
| 133 |
+
max_timestep_boundary: 1.0
|
| 134 |
+
min_timestep_boundary: 0.0
|
| 135 |
+
output_path: /mnt/data/limingleyang/openwam_checkpoints
|
| 136 |
+
save_steps: 2000
|
| 137 |
+
keep_last_k_ckpts: 1
|
| 138 |
+
finetune_ckpt_path: null
|
| 139 |
+
resume_ckpt_path: null
|
| 140 |
+
dataset_num_workers: 8
|
| 141 |
+
project:
|
| 142 |
+
name: open-wam
|
| 143 |
+
output_dir: outputs/${now:%Y-%m-%d_%H-%M-%S}
|
| 144 |
+
seed: 42
|
| 145 |
+
wandb:
|
| 146 |
+
project: open-wam
|
| 147 |
+
run_name: null
|
| 148 |
+
entity: null
|
sft/run10_3sys/private/assets/reason1/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
sft/run10_3sys/private/assets/reason1/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 32768,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 1280,
|
| 35 |
+
"intermediate_size": 3420,
|
| 36 |
+
"num_heads": 16,
|
| 37 |
+
"in_chans": 3,
|
| 38 |
+
"out_hidden_size": 3584,
|
| 39 |
+
"patch_size": 14,
|
| 40 |
+
"spatial_merge_size": 2,
|
| 41 |
+
"spatial_patch_size": 14,
|
| 42 |
+
"window_size": 112,
|
| 43 |
+
"fullatt_block_indexes": [
|
| 44 |
+
7,
|
| 45 |
+
15,
|
| 46 |
+
23,
|
| 47 |
+
31
|
| 48 |
+
],
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"temporal_patch_size": 2
|
| 51 |
+
},
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"type": "mrope",
|
| 54 |
+
"mrope_section": [
|
| 55 |
+
16,
|
| 56 |
+
24,
|
| 57 |
+
24
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
"vocab_size": 152064
|
| 61 |
+
}
|
sft/run10_3sys/private/assets/reason1/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.000001,
|
| 11 |
+
"transformers_version": "4.37.0"
|
| 12 |
+
}
|
sft/run10_3sys/private/assets/reason1/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
sft/run10_3sys/private/assets/reason1/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run10_3sys/private/assets/reason1/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"additional_special_tokens": [
|
| 182 |
+
"<|im_start|>",
|
| 183 |
+
"<|im_end|>",
|
| 184 |
+
"<|object_ref_start|>",
|
| 185 |
+
"<|object_ref_end|>",
|
| 186 |
+
"<|box_start|>",
|
| 187 |
+
"<|box_end|>",
|
| 188 |
+
"<|quad_start|>",
|
| 189 |
+
"<|quad_end|>",
|
| 190 |
+
"<|vision_start|>",
|
| 191 |
+
"<|vision_end|>",
|
| 192 |
+
"<|vision_pad|>",
|
| 193 |
+
"<|image_pad|>",
|
| 194 |
+
"<|video_pad|>"
|
| 195 |
+
],
|
| 196 |
+
"bos_token": null,
|
| 197 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"model_max_length": 131072,
|
| 202 |
+
"pad_token": "<|endoftext|>",
|
| 203 |
+
"split_special_tokens": false,
|
| 204 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 205 |
+
"unk_token": null,
|
| 206 |
+
"add_bos_token": false
|
| 207 |
+
}
|
sft/run10_3sys/private/assets/vlm_expert/chat_template.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
| 4 |
+
|
sft/run10_3sys/private/assets/vlm_expert/config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 151655,
|
| 6 |
+
"model_type": "qwen3_vl",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 151645,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 6144,
|
| 18 |
+
"max_position_embeddings": 262144,
|
| 19 |
+
"model_type": "qwen3_vl_text",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"mrope_interleaved": true,
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
24,
|
| 28 |
+
20,
|
| 29 |
+
20
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 5000000,
|
| 34 |
+
"tie_word_embeddings": true,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 151936
|
| 37 |
+
},
|
| 38 |
+
"tie_word_embeddings": true,
|
| 39 |
+
"transformers_version": "4.57.0.dev0",
|
| 40 |
+
"video_token_id": 151656,
|
| 41 |
+
"vision_config": {
|
| 42 |
+
"deepstack_visual_indexes": [
|
| 43 |
+
5,
|
| 44 |
+
11,
|
| 45 |
+
17
|
| 46 |
+
],
|
| 47 |
+
"depth": 24,
|
| 48 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 49 |
+
"hidden_size": 1024,
|
| 50 |
+
"in_channels": 3,
|
| 51 |
+
"initializer_range": 0.02,
|
| 52 |
+
"intermediate_size": 4096,
|
| 53 |
+
"model_type": "qwen3_vl",
|
| 54 |
+
"num_heads": 16,
|
| 55 |
+
"num_position_embeddings": 2304,
|
| 56 |
+
"out_hidden_size": 2048,
|
| 57 |
+
"patch_size": 16,
|
| 58 |
+
"spatial_merge_size": 2,
|
| 59 |
+
"temporal_patch_size": 2
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652
|
| 63 |
+
}
|
sft/run10_3sys/private/assets/vlm_expert/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_p": 0.8,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"repetition_penalty": 1.0,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
sft/run10_3sys/private/assets/vlm_expert/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run10_3sys/private/assets/vlm_expert/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
sft/run10_3sys/private/assets/vlm_expert/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run10_3sys/private/assets/vlm_expert/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
sft/run10_3sys/private/assets/vlm_expert/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
sft/run10_3sys/private/assets/vlm_expert/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run11_2sys_scratch_dinov3/private/assets/config.yaml
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
video_backbone:
|
| 3 |
+
name: cosmos_predict25_2b
|
| 4 |
+
model_path: /mnt/data/limingleyang/model/Cosmos-Predict2.5-2B
|
| 5 |
+
model_variant: base/post-trained
|
| 6 |
+
text_encoder_path: /mnt/data/limingleyang/model/Cosmos-Reason1-7B
|
| 7 |
+
text_encoder_dropout: 0.0
|
| 8 |
+
vae: none
|
| 9 |
+
shift_video: 5.0
|
| 10 |
+
from_scratch: true
|
| 11 |
+
encoder:
|
| 12 |
+
name: dinov3
|
| 13 |
+
model_path: /mnt/data/limingleyang/model/dinov3-vitb16-pretrain-lvd1689m
|
| 14 |
+
dit_patch_size:
|
| 15 |
+
- 1
|
| 16 |
+
- 1
|
| 17 |
+
- 1
|
| 18 |
+
svae_path: /mnt/data/limingleyang/openwam_svae/libero_dinov3_vitb16/svae48/svae.pt
|
| 19 |
+
svae_target_dim: 48
|
| 20 |
+
temporal_compression: 4
|
| 21 |
+
causal_temporal: true
|
| 22 |
+
dit_config:
|
| 23 |
+
max_img_h: 240
|
| 24 |
+
max_img_w: 240
|
| 25 |
+
max_frames: 128
|
| 26 |
+
in_channels: 48
|
| 27 |
+
out_channels: 48
|
| 28 |
+
patch_spatial: 1
|
| 29 |
+
patch_temporal: 1
|
| 30 |
+
model_channels: 2048
|
| 31 |
+
num_blocks: 28
|
| 32 |
+
num_heads: 16
|
| 33 |
+
concat_padding_mask: true
|
| 34 |
+
crossattn_emb_channels: 1024
|
| 35 |
+
use_crossattn_projection: true
|
| 36 |
+
crossattn_proj_in_channels: 100352
|
| 37 |
+
pos_emb_cls: rope3d
|
| 38 |
+
pos_emb_learnable: true
|
| 39 |
+
pos_emb_interpolation: crop
|
| 40 |
+
use_adaln_lora: true
|
| 41 |
+
adaln_lora_dim: 256
|
| 42 |
+
atten_backend: transformer_engine
|
| 43 |
+
extra_per_block_abs_pos_emb: false
|
| 44 |
+
rope_h_extrapolation_ratio: 3.0
|
| 45 |
+
rope_w_extrapolation_ratio: 3.0
|
| 46 |
+
rope_t_extrapolation_ratio: 1.0
|
| 47 |
+
rope_enable_fps_modulation: false
|
| 48 |
+
components:
|
| 49 |
+
- attr: text_encoder
|
| 50 |
+
source: state_dict
|
| 51 |
+
sub_module: reason1
|
| 52 |
+
- attr: vae
|
| 53 |
+
source: state_dict
|
| 54 |
+
sub_module: video_encoder
|
| 55 |
+
action_backbone:
|
| 56 |
+
dim: 1024
|
| 57 |
+
ffn_dim: 4096
|
| 58 |
+
shift_action: 5.0
|
| 59 |
+
freeze:
|
| 60 |
+
- video_backbone.text_encoder
|
| 61 |
+
- video_backbone.reason1
|
| 62 |
+
- video_backbone.vae
|
| 63 |
+
- video_backbone.image_encoder
|
| 64 |
+
- video_backbone.video_encoder
|
| 65 |
+
architecture:
|
| 66 |
+
framework: dual_system
|
| 67 |
+
variant: joint_self_attn
|
| 68 |
+
action_dim: 80
|
| 69 |
+
use_proprioception: true
|
| 70 |
+
state_dim: 80
|
| 71 |
+
bridge_layers: null
|
| 72 |
+
bridge_interval: 1
|
| 73 |
+
mot_checkpoint_mixed_attn: false
|
| 74 |
+
rope_mode: grouped
|
| 75 |
+
attention_mask_mode: mutual
|
| 76 |
+
video_attention_mask_mode: first_frame_causal
|
| 77 |
+
detach_bridge: false
|
| 78 |
+
idm_video_cond_noise_prob: 0.5
|
| 79 |
+
dataloader:
|
| 80 |
+
type: libero
|
| 81 |
+
dataset_dir: /mnt/data/wangyuran/benchmark_data/libero
|
| 82 |
+
action_mode: libero
|
| 83 |
+
gripper_convention: minus1_closed_plus1_open
|
| 84 |
+
unify_action: true
|
| 85 |
+
unify_action_map:
|
| 86 |
+
- 0-9
|
| 87 |
+
normalize_mode: min-max
|
| 88 |
+
head_camera_priority:
|
| 89 |
+
- observation.images.image
|
| 90 |
+
wrist_camera_priority:
|
| 91 |
+
- observation.images.wrist_image
|
| 92 |
+
- observation.images.image2
|
| 93 |
+
prompt_columns:
|
| 94 |
+
- language_instruction
|
| 95 |
+
- task
|
| 96 |
+
- prompt
|
| 97 |
+
num_frames: 33
|
| 98 |
+
video_stride: 4
|
| 99 |
+
window_stride: 1
|
| 100 |
+
height: 384
|
| 101 |
+
width: 320
|
| 102 |
+
multiview: true
|
| 103 |
+
split: train
|
| 104 |
+
enable_action_supervision: true
|
| 105 |
+
seed: 42
|
| 106 |
+
training:
|
| 107 |
+
debug: false
|
| 108 |
+
learning_rate: 0.0001
|
| 109 |
+
adam_betas:
|
| 110 |
+
- 0.9
|
| 111 |
+
- 0.95
|
| 112 |
+
weight_decay: 0.01
|
| 113 |
+
max_grad_norm: 1.0
|
| 114 |
+
num_epochs: 10
|
| 115 |
+
max_steps: null
|
| 116 |
+
batch_size: 8
|
| 117 |
+
gradient_accumulation_steps: 1
|
| 118 |
+
lr_scheduler: cosine
|
| 119 |
+
warmup_ratio: 0.05
|
| 120 |
+
lr_min_ratio: 0.01
|
| 121 |
+
vlm_warmup_ratio: 0.1
|
| 122 |
+
action_lr: null
|
| 123 |
+
video_lr: null
|
| 124 |
+
vlm_lr: 1.0e-05
|
| 125 |
+
mixed_precision: bf16
|
| 126 |
+
zero_stage: 2
|
| 127 |
+
use_gradient_checkpointing: false
|
| 128 |
+
use_gradient_checkpointing_offload: false
|
| 129 |
+
initialize_model_on_cpu: false
|
| 130 |
+
offload_optimizer_device: none
|
| 131 |
+
lambda_video: 1.0
|
| 132 |
+
lambda_action: 1.0
|
| 133 |
+
max_timestep_boundary: 1.0
|
| 134 |
+
min_timestep_boundary: 0.0
|
| 135 |
+
output_path: /mnt/data/limingleyang/openwam_checkpoints/run11_2sys_scratch_dinov3
|
| 136 |
+
save_steps: 2000
|
| 137 |
+
keep_last_k_ckpts: 1
|
| 138 |
+
finetune_ckpt_path: null
|
| 139 |
+
resume_ckpt_path: null
|
| 140 |
+
dataset_num_workers: 8
|
| 141 |
+
project:
|
| 142 |
+
name: open-wam
|
| 143 |
+
output_dir: outputs/${now:%Y-%m-%d_%H-%M-%S}
|
| 144 |
+
seed: 42
|
| 145 |
+
wandb:
|
| 146 |
+
project: open-wam
|
| 147 |
+
run_name: run11_2sys_scratch_dinov3
|
| 148 |
+
entity: null
|
sft/run11_2sys_scratch_dinov3/private/assets/dinov3/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DINOv3ViTModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"drop_path_rate": 0.0,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"image_size": 224,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"key_bias": false,
|
| 13 |
+
"layer_norm_eps": 1e-05,
|
| 14 |
+
"layerscale_value": 1.0,
|
| 15 |
+
"mlp_bias": true,
|
| 16 |
+
"model_type": "dinov3_vit",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_channels": 3,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"num_register_tokens": 4,
|
| 21 |
+
"patch_size": 16,
|
| 22 |
+
"pos_embed_jitter": null,
|
| 23 |
+
"pos_embed_rescale": 2.0,
|
| 24 |
+
"pos_embed_shift": null,
|
| 25 |
+
"proj_bias": true,
|
| 26 |
+
"query_bias": true,
|
| 27 |
+
"rope_theta": 100.0,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.56.0.dev0",
|
| 30 |
+
"use_gated_mlp": false,
|
| 31 |
+
"value_bias": true
|
| 32 |
+
}
|
sft/run11_2sys_scratch_dinov3/private/assets/reason1/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
sft/run11_2sys_scratch_dinov3/private/assets/reason1/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 32768,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 1280,
|
| 35 |
+
"intermediate_size": 3420,
|
| 36 |
+
"num_heads": 16,
|
| 37 |
+
"in_chans": 3,
|
| 38 |
+
"out_hidden_size": 3584,
|
| 39 |
+
"patch_size": 14,
|
| 40 |
+
"spatial_merge_size": 2,
|
| 41 |
+
"spatial_patch_size": 14,
|
| 42 |
+
"window_size": 112,
|
| 43 |
+
"fullatt_block_indexes": [
|
| 44 |
+
7,
|
| 45 |
+
15,
|
| 46 |
+
23,
|
| 47 |
+
31
|
| 48 |
+
],
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"temporal_patch_size": 2
|
| 51 |
+
},
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"type": "mrope",
|
| 54 |
+
"mrope_section": [
|
| 55 |
+
16,
|
| 56 |
+
24,
|
| 57 |
+
24
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
"vocab_size": 152064
|
| 61 |
+
}
|
sft/run11_2sys_scratch_dinov3/private/assets/reason1/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.000001,
|
| 11 |
+
"transformers_version": "4.37.0"
|
| 12 |
+
}
|
sft/run11_2sys_scratch_dinov3/private/assets/reason1/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
sft/run11_2sys_scratch_dinov3/private/assets/reason1/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run11_2sys_scratch_dinov3/private/assets/reason1/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"additional_special_tokens": [
|
| 182 |
+
"<|im_start|>",
|
| 183 |
+
"<|im_end|>",
|
| 184 |
+
"<|object_ref_start|>",
|
| 185 |
+
"<|object_ref_end|>",
|
| 186 |
+
"<|box_start|>",
|
| 187 |
+
"<|box_end|>",
|
| 188 |
+
"<|quad_start|>",
|
| 189 |
+
"<|quad_end|>",
|
| 190 |
+
"<|vision_start|>",
|
| 191 |
+
"<|vision_end|>",
|
| 192 |
+
"<|vision_pad|>",
|
| 193 |
+
"<|image_pad|>",
|
| 194 |
+
"<|video_pad|>"
|
| 195 |
+
],
|
| 196 |
+
"bos_token": null,
|
| 197 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"model_max_length": 131072,
|
| 202 |
+
"pad_token": "<|endoftext|>",
|
| 203 |
+
"split_special_tokens": false,
|
| 204 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 205 |
+
"unk_token": null,
|
| 206 |
+
"add_bos_token": false
|
| 207 |
+
}
|
sft/run11_2sys_scratch_dinov3/private/assets/svae_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"format_version": 2, "model_config": {"input_dim": 768, "latent_dim": 48, "num_heads": 16, "num_layers": 3, "intermediate_size": 2048, "dropout": 0.0}}
|
sft/run20_3sys_vlm_dino/private/assets/config.yaml
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
video_backbone:
|
| 3 |
+
name: cosmos_predict25_2b
|
| 4 |
+
model_path: /mnt/data/limingleyang/model/Cosmos-Predict2.5-2B
|
| 5 |
+
model_variant: base/post-trained
|
| 6 |
+
text_encoder_path: /mnt/data/limingleyang/model/Cosmos-Reason1-7B
|
| 7 |
+
text_encoder_dropout: 0.0
|
| 8 |
+
vae: wan2pt1
|
| 9 |
+
shift_video: 5.0
|
| 10 |
+
dit_config:
|
| 11 |
+
max_img_h: 240
|
| 12 |
+
max_img_w: 240
|
| 13 |
+
max_frames: 128
|
| 14 |
+
in_channels: 16
|
| 15 |
+
out_channels: 16
|
| 16 |
+
patch_spatial: 2
|
| 17 |
+
patch_temporal: 1
|
| 18 |
+
model_channels: 2048
|
| 19 |
+
num_blocks: 28
|
| 20 |
+
num_heads: 16
|
| 21 |
+
concat_padding_mask: true
|
| 22 |
+
crossattn_emb_channels: 1024
|
| 23 |
+
use_crossattn_projection: true
|
| 24 |
+
crossattn_proj_in_channels: 100352
|
| 25 |
+
pos_emb_cls: rope3d
|
| 26 |
+
pos_emb_learnable: true
|
| 27 |
+
pos_emb_interpolation: crop
|
| 28 |
+
use_adaln_lora: true
|
| 29 |
+
adaln_lora_dim: 256
|
| 30 |
+
atten_backend: transformer_engine
|
| 31 |
+
extra_per_block_abs_pos_emb: false
|
| 32 |
+
rope_h_extrapolation_ratio: 3.0
|
| 33 |
+
rope_w_extrapolation_ratio: 3.0
|
| 34 |
+
rope_t_extrapolation_ratio: 1.0
|
| 35 |
+
rope_enable_fps_modulation: false
|
| 36 |
+
components:
|
| 37 |
+
- attr: vae
|
| 38 |
+
source: state_dict
|
| 39 |
+
sub_module: vae
|
| 40 |
+
- attr: text_encoder
|
| 41 |
+
source: state_dict
|
| 42 |
+
sub_module: reason1
|
| 43 |
+
action_backbone:
|
| 44 |
+
dim: 1024
|
| 45 |
+
ffn_dim: 4096
|
| 46 |
+
shift_action: 5.0
|
| 47 |
+
vlm_expert:
|
| 48 |
+
checkpoint_path: /mnt/data/limingleyang/model/Qwen3-VL-2B-Instruct
|
| 49 |
+
load_pretrained: true
|
| 50 |
+
max_length: 512
|
| 51 |
+
input_mode: independent_views
|
| 52 |
+
freeze_vision_tower: true
|
| 53 |
+
freeze_embed_tokens: true
|
| 54 |
+
freeze_decoder_layers: false
|
| 55 |
+
run_full_tail: ${model.architecture.vlm_dino.enabled}
|
| 56 |
+
use_gradient_checkpointing: false
|
| 57 |
+
freeze:
|
| 58 |
+
- video_backbone.text_encoder
|
| 59 |
+
- video_backbone.reason1
|
| 60 |
+
- video_backbone.vae
|
| 61 |
+
- video_backbone.image_encoder
|
| 62 |
+
- video_backbone.video_encoder
|
| 63 |
+
architecture:
|
| 64 |
+
framework: tri_system
|
| 65 |
+
variant: joint_self_attn
|
| 66 |
+
action_dim: 80
|
| 67 |
+
use_proprioception: true
|
| 68 |
+
state_dim: 80
|
| 69 |
+
attention_mask_mode: mutual
|
| 70 |
+
video_attention_mask_mode: first_frame_causal
|
| 71 |
+
vlm_prefix_suffix:
|
| 72 |
+
enabled: false
|
| 73 |
+
num_layers: null
|
| 74 |
+
vlm_attn_warmup:
|
| 75 |
+
start_weight: 0.01
|
| 76 |
+
end_weight: 1.0
|
| 77 |
+
delay_ratio: 0.0
|
| 78 |
+
ramp_ratio: 0.05
|
| 79 |
+
shape: linear
|
| 80 |
+
mot_checkpoint_mixed_attn: false
|
| 81 |
+
bridge_layers: null
|
| 82 |
+
bridge_interval: 1
|
| 83 |
+
vlm_dino:
|
| 84 |
+
enabled: true
|
| 85 |
+
loss_weight: 0.004
|
| 86 |
+
cosine_weight: 0.2
|
| 87 |
+
num_patches: 256
|
| 88 |
+
num_query_tokens: 8
|
| 89 |
+
target_dim: 1024
|
| 90 |
+
head_layers: 1
|
| 91 |
+
head_heads: 4
|
| 92 |
+
head_dim_head: 32
|
| 93 |
+
head_ff_mult: 1
|
| 94 |
+
teacher_checkpoint_path: ${oc.env:OPENWAM_DINO_VIDEO_ROOT,''}/teacher_step_10000.pth
|
| 95 |
+
teacher_config_path: ${oc.env:OPENWAM_DINO_VIDEO_ROOT,''}/config.yaml
|
| 96 |
+
training_heads: true
|
| 97 |
+
dataloader:
|
| 98 |
+
type: libero
|
| 99 |
+
dataset_dir: /mnt/data/wangyuran/benchmark_data/libero
|
| 100 |
+
action_mode: libero
|
| 101 |
+
gripper_convention: minus1_closed_plus1_open
|
| 102 |
+
unify_action: true
|
| 103 |
+
unify_action_map:
|
| 104 |
+
- 0-9
|
| 105 |
+
normalize_mode: min-max
|
| 106 |
+
head_camera_priority:
|
| 107 |
+
- observation.images.image
|
| 108 |
+
wrist_camera_priority:
|
| 109 |
+
- observation.images.wrist_image
|
| 110 |
+
- observation.images.image2
|
| 111 |
+
prompt_columns:
|
| 112 |
+
- language_instruction
|
| 113 |
+
- task
|
| 114 |
+
- prompt
|
| 115 |
+
num_frames: 33
|
| 116 |
+
video_stride: 4
|
| 117 |
+
window_stride: 1
|
| 118 |
+
height: 384
|
| 119 |
+
width: 320
|
| 120 |
+
multiview: true
|
| 121 |
+
split: train
|
| 122 |
+
enable_action_supervision: true
|
| 123 |
+
vlm_dino: ${model.architecture.vlm_dino.enabled}
|
| 124 |
+
seed: 42
|
| 125 |
+
training:
|
| 126 |
+
debug: false
|
| 127 |
+
learning_rate: 0.0001
|
| 128 |
+
adam_betas:
|
| 129 |
+
- 0.9
|
| 130 |
+
- 0.95
|
| 131 |
+
weight_decay: 0.01
|
| 132 |
+
max_grad_norm: 1.0
|
| 133 |
+
num_epochs: 10
|
| 134 |
+
max_steps: null
|
| 135 |
+
batch_size: 4
|
| 136 |
+
gradient_accumulation_steps: 1
|
| 137 |
+
lr_scheduler: cosine
|
| 138 |
+
warmup_ratio: 0.05
|
| 139 |
+
lr_min_ratio: 0.01
|
| 140 |
+
vlm_warmup_ratio: 0.1
|
| 141 |
+
action_lr: null
|
| 142 |
+
video_lr: null
|
| 143 |
+
vlm_lr: 1.0e-05
|
| 144 |
+
mixed_precision: bf16
|
| 145 |
+
zero_stage: 2
|
| 146 |
+
use_gradient_checkpointing: false
|
| 147 |
+
use_gradient_checkpointing_offload: false
|
| 148 |
+
initialize_model_on_cpu: false
|
| 149 |
+
offload_optimizer_device: none
|
| 150 |
+
lambda_video: 1.0
|
| 151 |
+
lambda_action: 1.0
|
| 152 |
+
max_timestep_boundary: 1.0
|
| 153 |
+
min_timestep_boundary: 0.0
|
| 154 |
+
output_path: /mnt/data/limingleyang/openwam_checkpoints/run20_3sys_vlm_dino
|
| 155 |
+
save_steps: 2000
|
| 156 |
+
keep_last_k_ckpts: 1
|
| 157 |
+
finetune_ckpt_path: null
|
| 158 |
+
resume_ckpt_path: null
|
| 159 |
+
dataset_num_workers: 8
|
| 160 |
+
vlm_dino_lr: 0.0001
|
| 161 |
+
project:
|
| 162 |
+
name: open-wam
|
| 163 |
+
output_dir: outputs/${now:%Y-%m-%d_%H-%M-%S}
|
| 164 |
+
seed: 42
|
| 165 |
+
wandb:
|
| 166 |
+
project: open-wam
|
| 167 |
+
run_name: run20_3sys_vlm_dino
|
| 168 |
+
entity: null
|
sft/run20_3sys_vlm_dino/private/assets/reason1/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
sft/run20_3sys_vlm_dino/private/assets/reason1/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 32768,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 1280,
|
| 35 |
+
"intermediate_size": 3420,
|
| 36 |
+
"num_heads": 16,
|
| 37 |
+
"in_chans": 3,
|
| 38 |
+
"out_hidden_size": 3584,
|
| 39 |
+
"patch_size": 14,
|
| 40 |
+
"spatial_merge_size": 2,
|
| 41 |
+
"spatial_patch_size": 14,
|
| 42 |
+
"window_size": 112,
|
| 43 |
+
"fullatt_block_indexes": [
|
| 44 |
+
7,
|
| 45 |
+
15,
|
| 46 |
+
23,
|
| 47 |
+
31
|
| 48 |
+
],
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"temporal_patch_size": 2
|
| 51 |
+
},
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"type": "mrope",
|
| 54 |
+
"mrope_section": [
|
| 55 |
+
16,
|
| 56 |
+
24,
|
| 57 |
+
24
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
"vocab_size": 152064
|
| 61 |
+
}
|
sft/run20_3sys_vlm_dino/private/assets/reason1/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.000001,
|
| 11 |
+
"transformers_version": "4.37.0"
|
| 12 |
+
}
|
sft/run20_3sys_vlm_dino/private/assets/reason1/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
sft/run20_3sys_vlm_dino/private/assets/reason1/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/run20_3sys_vlm_dino/private/assets/reason1/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"additional_special_tokens": [
|
| 182 |
+
"<|im_start|>",
|
| 183 |
+
"<|im_end|>",
|
| 184 |
+
"<|object_ref_start|>",
|
| 185 |
+
"<|object_ref_end|>",
|
| 186 |
+
"<|box_start|>",
|
| 187 |
+
"<|box_end|>",
|
| 188 |
+
"<|quad_start|>",
|
| 189 |
+
"<|quad_end|>",
|
| 190 |
+
"<|vision_start|>",
|
| 191 |
+
"<|vision_end|>",
|
| 192 |
+
"<|vision_pad|>",
|
| 193 |
+
"<|image_pad|>",
|
| 194 |
+
"<|video_pad|>"
|
| 195 |
+
],
|
| 196 |
+
"bos_token": null,
|
| 197 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"model_max_length": 131072,
|
| 202 |
+
"pad_token": "<|endoftext|>",
|
| 203 |
+
"split_special_tokens": false,
|
| 204 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 205 |
+
"unk_token": null,
|
| 206 |
+
"add_bos_token": false
|
| 207 |
+
}
|
sft/run20_3sys_vlm_dino/private/assets/vlm_expert/chat_template.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
| 4 |
+
|