modelscope
为什么Qwen_Image的推理代码里面的text_encoder部分和modelscope以及huggingface里面的text_encoder的权重中的key值对不上？
我采用下面的代码来单次推理Qwen_image:
import glob
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch
import os
os.environ["PYTHONBREAKPOINT"] = "0"
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(path=['/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00001-of-00004.safetensors', '/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00002-of-00004.safetensors', '/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00003-of-00004.safetensors', '/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00004-of-00004.safetensors']),
ModelConfig(path= "/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/vae/diffusion_pytorch_model.safetensors"),
ModelConfig(path=['/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00001-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00002-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00003-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00004-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00005-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00006-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00007-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00008-of-00009.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/transformer/diffusion_pytorch_model-00009-of-00009.safetensors']),
],
tokenizer_config=ModelConfig(path="/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/tokenizer/"),
)
prompt = "A detailed portrait of a girl underwater, wearing a blue flowing dress, hair gently floating, clear light and shadow, surrounded by bubbles, calm expression, fine details, dreamy and beautiful."
image = pipe(
prompt, seed=0, num_inference_steps=40,
)
image.save("image.jpg")
已知我的权重可以在huggingface提供的官方代码跑通，这证明我的权重没有问题，但是我在运行的时候报错了，报错说明代码需要的权重和我给出的权重对应不上，请问为什么会出现这样的问题？感谢！！！
报错如下：
(qwen_image)[DiffSynth-Studio]$ python lkwtest3.py Loading models from: ['/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/model/model-00001-of-00004.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/model/model-00002-of-00004.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/model/model-00003-of-00004.safetensors', '/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/model/model-00004-of-00004.safetensors'] model_name: qwen_image_text_encoder model_class: QwenImageTextEncoder 111111 Traceback (most recent call last): File "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/DiffSynth-Studio/lkwtest3.py", line 7, in <module> pipe = QwenImagePipeline.from_pretrained( File "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/DiffSynth-Studio/diffsynth/pipelines/qwen_image.py", line 332, in from_pretrained model_manager.load_model( File "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/DiffSynth-Studio/diffsynth/models/model_manager.py", line 418, in load_model model_names, models = model_detector.load( File "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/DiffSynth-Studio/diffsynth/models/model_manager.py", line 192, in load loaded_model_names, loaded_models = load_model_from_single_file(state_dict, model_names, model_classes, model_resource, torch_dtype, device) File "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/likaiwen/PythonProjects/Qwen_image_train/DiffSynth-Studio/diffsynth/models/model_manager.py", line 83, in load_model_from_single_file model.load_state_dict(model_state_dict, assign=True) File "/home/hadoop-automaterials/dolphinfs_hdd_hadoop-automaterials/likaiwen/lkwanaconda/envc/qwen_image/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2584, in load_state_dict raise RuntimeError( RuntimeError: Error(s) in loading state_dict for QwenImageTextEncoder: Missing key(s) in state_dict: "model.embed_tokens.weight", "model.layers.0.self_attn.q_proj.weight", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.k_proj.weight", "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.v_proj.weight", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.self_attn.o_proj.weight", "model.layers.0.mlp.gate_proj.weight", "model.layers.0.mlp.up_proj.weight", "model.layers.0.mlp.down_proj.weight", "model.layers.0.input_layernorm.weight", "model.layers.0.post_attention_layernorm.weight", "model.layers.1.self_attn.q_proj.weight", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.k_proj.weight", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.v_proj.weight", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.self_attn.o_proj.weight", "model.layers.1.mlp.gate_proj.weight", "model.layers.1.mlp.up_proj.weight", "model.layers.1.mlp.down_proj.weight", "model.layers.1.input_layernorm.weight", "model.layers.1.post_attention_layernorm.weight", "model.layers.2.self_attn.q_proj.weight", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.k_proj.weight", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.v_proj.weight", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.self_attn.o_proj.weight", "model.layers.2.mlp.gate_proj.weight", "model.layers.2.mlp.up_proj.weight", "model.layers.2.mlp.down_proj.weight", "model.layers.2.input_layernorm.weight", "model.layers.2.post_attention_layernorm.weight", "model.layers.3.self_attn.q_proj.weight", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.k_proj.weight", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.v_proj.weight", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.self_attn.o_proj.weight", "model.layers.3.mlp.gate_proj.weight", "model.layers.3.mlp.up_proj.weight", "model.layers.3.mlp.down_proj.weight", "model.layers.3.input_layernorm.weight", "model.layers.3.post_attention_layernorm.weight", "model.layers.4.self_attn.q_proj.weight", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.k_proj.weight", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.v_proj.weight", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.self_attn.o_proj.weight", "model.layers.4.mlp.gate_proj.weight", "model.layers.4.mlp.up_proj.weight", "model.layers.4.mlp.down_proj.weight", "model.layers.4.input_layernorm.weight", "model.layers.4.post_attention_layernorm.weight", "model.layers.5.self_attn.q_proj.weight", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.k_proj.weight", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.v_proj.weight", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.self_attn.o_proj.weight", "model.layers.5.mlp.gate_proj.weight", "model.layers.5.mlp.up_proj.weight", "model.layers.5.mlp.down_proj.weight", "model.layers.5.input_layernorm.weight", "model.layers.5.post_attention_layernorm.weight", "model.layers.6.self_attn.q_proj.weight", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.k_proj.weight", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.v_proj.weight", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.self_attn.o_proj.weight", "model.layers.6.mlp.gate_proj.weight", "model.layers.6.mlp.up_proj.weight", "model.layers.6.mlp.down_proj.weight", "model.layers.6.input_layernorm.weight", "model.layers.6.post_attention_layernorm.weight", "model.layers.7.self_attn.q_proj.weight", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.k_proj.weight", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.v_proj.weight", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.self_attn.o_proj.weight", "model.layers.7.mlp.gate_proj.weight", "model.layers.7.mlp.up_proj.weight", "model.layers.7.mlp.down_proj.weight", "model.layers.7.input_layernorm.weight", "model.layers.7.post_attention_layernorm.weight", "model.layers.8.self_attn.q_proj.weight", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.k_proj.weight", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.v_proj.weight", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.self_attn.o_proj.weight", "model.layers.8.mlp.gate_proj.weight", "model.layers.8.mlp.up_proj.weight", "model.layers.8.mlp.down_proj.weight", "model.layers.8.input_layernorm.weight", "model.layers.8.post_attention_layernorm.weight", "model.layers.9.self_attn.q_proj.weight", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.k_proj.weight", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.v_proj.weight", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.self_attn.o_proj.weight", "model.layers.9.mlp.gate_proj.weight", "model.layers.9.mlp.up_proj.weight", "model.layers.9.mlp.down_proj.weight", "model.layers.9.input_layernorm.weight", "model.layers.9.post_attention_layernorm.weight", "model.layers.10.self_attn.q_proj.weight", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.k_proj.weight", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.v_proj.weight", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.self_attn.o_proj.weight", "model.layers.10.mlp.gate_proj.weight", "model.layers.10.mlp.up_proj.weight", "model.layers.10.mlp.down_proj.weight", "model.layers.10.input_layernorm.weight", "model.layers.10.post_attention_layernorm.weight", "model.layers.11.self_attn.q_proj.weight", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.k_proj.weight", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.v_proj.weight", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.self_attn.o_proj.weight", "model.layers.11.mlp.gate_proj.weight", "model.layers.11.mlp.up_proj.weight", "model.layers.11.mlp.down_proj.weight", "model.layers.11.input_layernorm.weight", "model.layers.11.post_attention_layernorm.weight", "model.layers.12.self_attn.q_proj.weight", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.k_proj.weight", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.v_proj.weight", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.self_attn.o_proj.weight", "model.layers.12.mlp.gate_proj.weight", "model.layers.12.mlp.up_proj.weight", "model.layers.12.mlp.down_proj.weight", "model.layers.12.input_layernorm.weight", "model.layers.12.post_attention_layernorm.weight", "model.layers.13.self_attn.q_proj.weight", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.k_proj.weight", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.v_proj.weight", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.self_attn.o_proj.weight", "model.layers.13.mlp.gate_proj.weight", "model.layers.13.mlp.up_proj.weight", "model.layers.13.mlp.down_proj.weight", "model.layers.13.input_layernorm.weight", "model.layers.13.post_attention_layernorm.weight", "model.layers.14.self_attn.q_proj.weight", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.k_proj.weight", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.v_proj.weight", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.self_attn.o_proj.weight", "model.layers.14.mlp.gate_proj.weight", "model.layers.14.mlp.up_proj.weight", "model.layers.14.mlp.down_proj.weight", "model.layers.14.input_layernorm.weight", "model.layers.14.post_attention_layernorm.weight", "model.layers.15.self_attn.q_proj.weight", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.k_proj.weight", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.v_proj.weight", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.self_attn.o_proj.weight", "model.layers.15.mlp.gate_proj.weight", "model.layers.15.mlp.up_proj.weight", "model.layers.15.mlp.down_proj.weight", "model.layers.15.input_layernorm.weight", "model.layers.15.post_attention_layernorm.weight", "model.layers.16.self_attn.q_proj.weight", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.k_proj.weight", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.v_proj.weight", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.self_attn.o_proj.weight", "model.layers.16.mlp.gate_proj.weight", "model.layers.16.mlp.up_proj.weight", "model.layers.16.mlp.down_proj.weight", "model.layers.16.input_layernorm.weight", "model.layers.16.post_attention_layernorm.weight", "model.layers.17.self_attn.q_proj.weight", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.k_proj.weight", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.v_proj.weight", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.self_attn.o_proj.weight", "model.layers.17.mlp.gate_proj.weight", "model.layers.17.mlp.up_proj.weight", "model.layers.17.mlp.down_proj.weight", "model.layers.17.input_layernorm.weight", "model.layers.17.post_attention_layernorm.weight", "model.layers.18.self_attn.q_proj.weight", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.k_proj.weight", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.v_proj.weight", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.self_attn.o_proj.weight", "model.layers.18.mlp.gate_proj.weight", "model.layers.18.mlp.up_proj.weight", "model.layers.18.mlp.down_proj.weight", "model.layers.18.input_layernorm.weight", "model.layers.18.post_attention_layernorm.weight", "model.layers.19.self_attn.q_proj.weight", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.k_proj.weight", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.v_proj.weight", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.self_attn.o_proj.weight", "model.layers.19.mlp.gate_proj.weight", "model.layers.19.mlp.up_proj.weight", "model.layers.19.mlp.down_proj.weight", "model.layers.19.input_layernorm.weight", "model.layers.19.post_attention_layernorm.weight", "model.layers.20.self_attn.q_proj.weight", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.k_proj.weight", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.v_proj.weight", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.self_attn.o_proj.weight", "model.layers.20.mlp.gate_proj.weight", "model.layers.20.mlp.up_proj.weight", "model.layers.20.mlp.down_proj.weight", "model.layers.20.input_layernorm.weight", "model.layers.20.post_attention_layernorm.weight", "model.layers.21.self_attn.q_proj.weight", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.k_proj.weight", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.v_proj.weight", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.self_attn.o_proj.weight", "model.layers.21.mlp.gate_proj.weight", "model.layers.21.mlp.up_proj.weight", "model.layers.21.mlp.down_proj.weight", "model.layers.21.input_layernorm.weight", "model.layers.21.post_attention_layernorm.weight", "model.layers.22.self_attn.q_proj.weight", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.k_proj.weight", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.v_proj.weight", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.self_attn.o_proj.weight", "model.layers.22.mlp.gate_proj.weight", "model.layers.22.mlp.up_proj.weight", "model.layers.22.mlp.down_proj.weight", "model.layers.22.input_layernorm.weight", "model.layers.22.post_attention_layernorm.weight", "model.layers.23.self_attn.q_proj.weight", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.k_proj.weight", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.v_proj.weight", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.self_attn.o_proj.weight", "model.layers.23.mlp.gate_proj.weight", "model.layers.23.mlp.up_proj.weight", "model.layers.23.mlp.down_proj.weight", "model.layers.23.input_layernorm.weight", "model.layers.23.post_attention_layernorm.weight", "model.layers.24.self_attn.q_proj.weight", "model.layers.24.self_attn.q_proj.bias", "model.layers.24.self_attn.k_proj.weight", "model.layers.24.self_attn.k_proj.bias", "model.layers.24.self_attn.v_proj.weight", "model.layers.24.self_attn.v_proj.bias", "model.layers.24.self_attn.o_proj.weight", "model.layers.24.mlp.gate_proj.weight", "model.layers.24.mlp.up_proj.weight", "model.layers.24.mlp.down_proj.weight", "model.layers.24.input_layernorm.weight", "model.layers.24.post_attention_layernorm.weight", "model.layers.25.self_attn.q_proj.weight", "model.layers.25.self_attn.q_proj.bias", "model.layers.25.self_attn.k_proj.weight", "model.layers.25.self_attn.k_proj.bias", "model.layers.25.self_attn.v_proj.weight", "model.layers.25.self_attn.v_proj.bias", "model.layers.25.self_attn.o_proj.weight", "model.layers.25.mlp.gate_proj.weight", "model.layers.25.mlp.up_proj.weight", "model.layers.25.mlp.down_proj.weight", "model.layers.25.input_layernorm.weight", "model.layers.25.post_attention_layernorm.weight", "model.layers.26.self_attn.q_proj.weight", "model.layers.26.self_attn.q_proj.bias", "model.layers.26.self_attn.k_proj.weight", "model.layers.26.self_attn.k_proj.bias", "model.layers.26.self_attn.v_proj.weight", "model.layers.26.self_attn.v_proj.bias", "model.layers.26.self_attn.o_proj.weight", "model.layers.26.mlp.gate_proj.weight", "model.layers.26.mlp.up_proj.weight", "model.layers.26.mlp.down_proj.weight", "model.layers.26.input_layernorm.weight", "model.layers.26.post_attention_layernorm.weight", "model.layers.27.self_attn.q_proj.weight", "model.layers.27.self_attn.q_proj.bias", "model.layers.27.self_attn.k_proj.weight", "model.layers.27.self_attn.k_proj.bias", "model.layers.27.self_attn.v_proj.weight", "model.layers.27.self_attn.v_proj.bias", "model.layers.27.self_attn.o_proj.weight", "model.layers.27.mlp.gate_proj.weight", "model.layers.27.mlp.up_proj.weight", "model.layers.27.mlp.down_proj.weight", "model.layers.27.input_layernorm.weight", "model.layers.27.post_attention_layernorm.weight", "model.norm.weight". Unexpected key(s) in state_dict: "model.language_model.embed_tokens.weight", "model.language_model.layers.0.input_layernorm.weight", "model.language_model.layers.0.mlp.down_proj.weight", "model.language_model.layers.0.mlp.gate_proj.weight", "model.language_model.layers.0.mlp.up_proj.weight", "model.language_model.layers.0.post_attention_layernorm.weight", "model.language_model.layers.0.self_attn.k_proj.bias", "model.language_model.layers.0.self_attn.k_proj.weight", "model.language_model.layers.0.self_attn.o_proj.weight", "model.language_model.layers.0.self_attn.q_proj.bias", "model.language_model.layers.0.self_attn.q_proj.weight", "model.language_model.layers.0.self_attn.v_proj.bias", "model.language_model.layers.0.self_attn.v_proj.weight", "model.language_model.layers.1.input_layernorm.weight", "model.language_model.layers.1.mlp.down_proj.weight", "model.language_model.layers.1.mlp.gate_proj.weight", "model.language_model.layers.1.mlp.up_proj.weight", "model.language_model.layers.1.post_attention_layernorm.weight", "model.language_model.layers.1.self_attn.k_proj.bias", "model.language_model.layers.1.self_attn.k_proj.weight", "model.language_model.layers.1.self_attn.o_proj.weight", "model.language_model.layers.1.self_attn.q_proj.bias", "model.language_model.layers.1.self_attn.q_proj.weight", "model.language_model.layers.1.self_attn.v_proj.bias", "model.language_model.layers.1.self_attn.v_proj.weight", "model.language_model.layers.2.input_layernorm.weight", "model.language_model.layers.2.mlp.down_proj.weight", "model.language_model.layers.2.mlp.gate_proj.weight", "model.language_model.layers.2.mlp.up_proj.weight", "model.language_model.layers.2.post_attention_layernorm.weight", "model.language_model.layers.2.self_attn.k_proj.bias", "model.language_model.layers.2.self_attn.k_proj.weight", "model.language_model.layers.2.self_attn.o_proj.weight", "model.language_model.layers.2.self_attn.q_proj.bias", "model.language_model.layers.2.self_attn.q_proj.weight", "model.language_model.layers.2.self_attn.v_proj.bias", "model.language_model.layers.2.self_attn.v_proj.weight", "model.language_model.layers.3.input_layernorm.weight", "model.language_model.layers.3.mlp.down_proj.weight", "model.language_model.layers.3.mlp.gate_proj.weight", "model.language_model.layers.3.mlp.up_proj.weight", "model.language_model.layers.3.post_attention_layernorm.weight", "model.language_model.layers.3.self_attn.k_proj.bias", "model.language_model.layers.3.self_attn.k_proj.weight", "model.language_model.layers.3.self_attn.o_proj.weight", "model.language_model.layers.3.self_attn.q_proj.bias", "model.language_model.layers.3.self_attn.q_proj.weight", "model.language_model.layers.3.self_attn.v_proj.bias", "model.language_model.layers.3.self_attn.v_proj.weight", "model.language_model.layers.4.input_layernorm.weight", "model.language_model.layers.4.mlp.down_proj.weight", "model.language_model.layers.4.mlp.gate_proj.weight", "model.language_model.layers.4.mlp.up_proj.weight", "model.language_model.layers.4.post_attention_layernorm.weight", "model.language_model.layers.4.self_attn.k_proj.bias", "model.language_model.layers.4.self_attn.k_proj.weight", "model.language_model.layers.4.self_attn.o_proj.weight", "model.language_model.layers.4.self_attn.q_proj.bias", "model.language_model.layers.4.self_attn.q_proj.weight", "model.language_model.layers.4.self_attn.v_proj.bias", "model.language_model.layers.4.self_attn.v_proj.weight", "model.language_model.layers.5.mlp.gate_proj.weight", "model.language_model.layers.5.self_attn.k_proj.bias", "model.language_model.layers.5.self_attn.k_proj.weight", "model.language_model.layers.5.self_attn.o_proj.weight", "model.language_model.layers.5.self_attn.q_proj.bias", "model.language_model.layers.5.self_attn.q_proj.weight", "model.language_model.layers.5.self_attn.v_proj.bias", "model.language_model.layers.5.self_attn.v_proj.weight", "model.visual.blocks.0.attn.proj.bias", "model.visual.blocks.0.attn.proj.weight", "model.visual.blocks.0.attn.qkv.bias", "model.visual.blocks.0.attn.qkv.weight", "model.visual.blocks.0.mlp.down_proj.bias", "model.visual.blocks.0.mlp.down_proj.weight", "model.visual.blocks.0.mlp.gate_proj.bias", "model.visual.blocks.0.mlp.gate_proj.weight", "model.visual.blocks.0.mlp.up_proj.bias", "model.visual.blocks.0.mlp.up_proj.weight", "model.visual.blocks.0.norm1.weight", "model.visual.blocks.0.norm2.weight", "model.visual.blocks.1.attn.proj.bias", "model.visual.blocks.1.attn.proj.weight", "model.visual.blocks.1.attn.qkv.bias", "model.visual.blocks.1.attn.qkv.weight", "model.visual.blocks.1.mlp.down_proj.bias", "model.visual.blocks.1.mlp.down_proj.weight", "model.visual.blocks.1.mlp.gate_proj.bias", "model.visual.blocks.1.mlp.gate_proj.weight", "model.visual.blocks.1.mlp.up_proj.bias", "model.visual.blocks.1.mlp.up_proj.weight", "model.visual.blocks.1.norm1.weight", "model.visual.blocks.1.norm2.weight", "model.visual.blocks.10.attn.proj.bias", "model.visual.blocks.10.attn.proj.weight", "model.visual.blocks.10.attn.qkv.bias", "model.visual.blocks.10.attn.qkv.weight", "model.visual.blocks.10.mlp.down_proj.bias", "model.visual.blocks.10.mlp.down_proj.weight", "model.visual.blocks.10.mlp.gate_proj.bias", "model.visual.blocks.10.mlp.gate_proj.weight", "model.visual.blocks.10.mlp.up_proj.bias", "model.visual.blocks.10.mlp.up_proj.weight", "model.visual.blocks.10.norm1.weight", "model.visual.blocks.10.norm2.weight", "model.visual.blocks.11.attn.proj.bias", "model.visual.blocks.11.attn.proj.weight", "model.visual.blocks.11.attn.qkv.bias", "model.visual.blocks.11.attn.qkv.weight", "model.visual.blocks.11.mlp.down_proj.bias", "model.visual.blocks.11.mlp.down_proj.weight", "model.visual.blocks.11.mlp.gate_proj.bias", "model.visual.blocks.11.mlp.gate_proj.weight", "model.visual.blocks.11.mlp.up_proj.bias", "model.visual.blocks.11.mlp.up_proj.weight", "model.visual.blocks.11.norm1.weight", "model.visual.blocks.11.norm2.weight", "model.visual.blocks.12.attn.proj.bias", "model.visual.blocks.12.attn.proj.weight", "model.visual.blocks.12.attn.qkv.bias", "model.visual.blocks.12.attn.qkv.weight", "model.visual.blocks.12.mlp.down_proj.bias", "model.visual.blocks.12.mlp.down_proj.weight", "model.visual.blocks.12.mlp.gate_proj.bias", "model.visual.blocks.12.mlp.gate_proj.weight", "model.visual.blocks.12.mlp.up_proj.bias", "model.visual.blocks.12.mlp.up_proj.weight", "model.visual.blocks.12.norm1.weight", "model.visual.blocks.12.norm2.weight", "model.visual.blocks.13.attn.proj.bias", "model.visual.blocks.13.attn.proj.weight", "model.visual.blocks.13.attn.qkv.bias", "model.visual.blocks.13.attn.qkv.weight", "model.visual.blocks.13.mlp.down_proj.bias", "model.visual.blocks.13.mlp.down_proj.weight", "model.visual.blocks.13.mlp.gate_proj.bias", "model.visual.blocks.13.mlp.gate_proj.weight", "model.visual.blocks.13.mlp.up_proj.bias", "model.visual.blocks.13.mlp.up_proj.weight", "model.visual.blocks.13.norm1.weight", "model.visual.blocks.13.norm2.weight", "model.visual.blocks.14.attn.proj.bias", "model.visual.blocks.14.attn.proj.weight", "model.visual.blocks.14.attn.qkv.bias", "model.visual.blocks.14.attn.qkv.weight", "model.visual.blocks.14.mlp.down_proj.bias", "model.visual.blocks.14.mlp.down_proj.weight", "model.visual.blocks.14.mlp.gate_proj.bias", "model.visual.blocks.14.mlp.gate_proj.weight", "model.visual.blocks.14.mlp.up_proj.bias", "model.visual.blocks.14.mlp.up_proj.weight", "model.visual.blocks.14.norm1.weight", "model.visual.blocks.14.norm2.weight", "model.visual.blocks.15.attn.proj.bias", "model.visual.blocks.15.attn.proj.weight", "model.visual.blocks.15.attn.qkv.bias", "model.visual.blocks.15.attn.qkv.weight", "model.visual.blocks.15.mlp.down_proj.bias", "model.visual.blocks.15.mlp.down_proj.weight", "model.visual.blocks.15.mlp.gate_proj.bias", "model.visual.blocks.15.mlp.gate_proj.weight", "model.visual.blocks.15.mlp.up_proj.bias", "model.visual.blocks.15.mlp.up_proj.weight", "model.visual.blocks.15.norm1.weight", "model.visual.blocks.15.norm2.weight", "model.visual.blocks.16.attn.proj.bias", "model.visual.blocks.16.attn.proj.weight", "model.visual.blocks.16.attn.qkv.bias", "model.visual.blocks.16.attn.qkv.weight", "model.visual.blocks.16.mlp.down_proj.bias", "model.visual.blocks.16.mlp.down_proj.weight", "model.visual.blocks.16.mlp.gate_proj.bias", "model.visual.blocks.16.mlp.gate_proj.weight", "model.visual.blocks.16.mlp.up_proj.bias", "model.visual.blocks.16.mlp.up_proj.weight", "model.visual.blocks.16.norm1.weight", "model.visual.blocks.16.norm2.weight", "model.visual.blocks.17.attn.proj.bias", "model.visual.blocks.17.attn.proj.weight", "model.visual.blocks.17.attn.qkv.bias", "model.visual.blocks.17.attn.qkv.weight", "model.visual.blocks.17.mlp.down_proj.bias", "model.visual.blocks.17.mlp.down_proj.weight", "model.visual.blocks.17.mlp.gate_proj.bias", "model.visual.blocks.17.mlp.gate_proj.weight", "model.visual.blocks.17.mlp.up_proj.bias", "model.visual.blocks.17.mlp.up_proj.weight", "model.visual.blocks.17.norm1.weight", "model.visual.blocks.17.norm2.weight", "model.visual.blocks.18.attn.proj.bias", "model.visual.blocks.18.attn.proj.weight", "model.visual.blocks.18.attn.qkv.bias", "model.visual.blocks.18.attn.qkv.weight", "model.visual.blocks.18.mlp.down_proj.bias", "model.visual.blocks.18.mlp.down_proj.weight", "model.visual.blocks.18.mlp.gate_proj.bias", "model.visual.blocks.18.mlp.gate_proj.weight", "model.visual.blocks.18.mlp.up_proj.bias", "model.visual.blocks.18.mlp.up_proj.weight", "model.visual.blocks.18.norm1.weight", "model.visual.blocks.18.norm2.weight", "model.visual.blocks.19.attn.proj.bias", "model.visual.blocks.19.attn.proj.weight", "model.visual.blocks.19.attn.qkv.bias", "model.visual.blocks.19.attn.qkv.weight", "model.visual.blocks.19.mlp.down_proj.bias", "model.visual.blocks.19.mlp.down_proj.weight", "model.visual.blocks.19.mlp.gate_proj.bias", "model.visual.blocks.19.mlp.gate_proj.weight", "model.visual.blocks.19.mlp.up_proj.bias", "model.visual.blocks.19.mlp.up_proj.weight", "model.visual.blocks.19.norm1.weight", "model.visual.blocks.19.norm2.weight", "model.visual.blocks.2.attn.proj.bias", "model.visual.blocks.2.attn.proj.weight", "model.visual.blocks.2.attn.qkv.bias", "model.visual.blocks.2.attn.qkv.weight", "model.visual.blocks.2.mlp.down_proj.bias", "model.visual.blocks.2.mlp.down_proj.weight", "model.visual.blocks.2.mlp.gate_proj.bias", "model.visual.blocks.2.mlp.gate_proj.weight", "model.visual.blocks.2.mlp.up_proj.bias", "model.visual.blocks.2.mlp.up_proj.weight", "model.visual.blocks.2.norm1.weight", "model.visual.blocks.2.norm2.weight", "model.visual.blocks.20.attn.proj.bias", "model.visual.blocks.20.attn.proj.weight", "model.visual.blocks.20.attn.qkv.bias", "model.visual.blocks.20.attn.qkv.weight", "model.visual.blocks.20.mlp.down_proj.bias", "model.visual.blocks.20.mlp.down_proj.weight", "model.visual.blocks.20.mlp.gate_proj.bias", "model.visual.blocks.20.mlp.gate_proj.weight", "model.visual.blocks.20.mlp.up_proj.bias", "model.visual.blocks.20.mlp.up_proj.weight", "model.visual.blocks.20.norm1.weight", "model.visual.blocks.20.norm2.weight", "model.visual.blocks.21.attn.proj.bias", "model.visual.blocks.21.attn.proj.weight", "model.visual.blocks.21.attn.qkv.bias", "model.visual.blocks.21.attn.qkv.weight", "model.visual.blocks.21.mlp.down_proj.bias", "model.visual.blocks.21.mlp.down_proj.weight", "model.visual.blocks.21.mlp.gate_proj.bias", "model.visual.blocks.21.mlp.gate_proj.weight", "model.visual.blocks.21.mlp.up_proj.bias", "model.visual.blocks.21.mlp.up_proj.weight", "model.visual.blocks.21.norm1.weight", "model.visual.blocks.21.norm2.weight", "model.visual.blocks.22.attn.proj.bias", "model.visual.blocks.22.attn.proj.weight", "model.visual.blocks.22.attn.qkv.bias", "model.visual.blocks.22.attn.qkv.weight", "model.visual.blocks.22.mlp.down_proj.bias", "model.visual.blocks.22.mlp.down_proj.weight", "model.visual.blocks.22.mlp.gate_proj.bias", "model.visual.blocks.22.mlp.gate_proj.weight", "model.visual.blocks.22.mlp.up_proj.bias", "model.visual.blocks.22.mlp.up_proj.weight", "model.visual.blocks.22.norm1.weight", "model.visual.blocks.22.norm2.weight", "model.visual.blocks.23.attn.proj.bias", "model.visual.blocks.23.attn.proj.weight", "model.visual.blocks.23.attn.qkv.bias", "model.visual.blocks.23.attn.qkv.weight", "model.visual.blocks.23.mlp.down_proj.bias", "model.visual.blocks.23.mlp.down_proj.weight", "model.visual.blocks.23.mlp.gate_proj.bias", "model.visual.blocks.23.mlp.gate_proj.weight", "model.visual.blocks.23.mlp.up_proj.bias", "model.visual.blocks.23.mlp.up_proj.weight", "model.visual.blocks.23.norm1.weight", "model.visual.blocks.23.norm2.weight", "model.visual.blocks.24.attn.proj.bias", "model.visual.blocks.24.attn.proj.weight", "model.visual.blocks.24.attn.qkv.bias", "model.visual.blocks.24.attn.qkv.weight", "model.visual.blocks.24.mlp.down_proj.bias", "model.visual.blocks.24.mlp.down_proj.weight", "model.visual.blocks.24.mlp.gate_proj.bias", "model.visual.blocks.24.mlp.gate_proj.weight", "model.visual.blocks.24.mlp.up_proj.bias", "model.visual.blocks.24.mlp.up_proj.weight", "model.visual.blocks.24.norm1.weight", "model.visual.blocks.24.norm2.weight", "model.visual.blocks.25.attn.proj.bias", "model.visual.blocks.25.attn.proj.weight", "model.visual.blocks.25.attn.qkv.bias", "model.visual.blocks.25.attn.qkv.weight", "model.visual.blocks.25.mlp.down_proj.bias", "model.visual.blocks.25.mlp.down_proj.weight", "model.visual.blocks.25.mlp.gate_proj.bias", "model.visual.blocks.25.mlp.gate_proj.weight", "model.visual.blocks.25.mlp.up_proj.bias", "model.visual.blocks.25.mlp.up_proj.weight", "model.visual.blocks.25.norm1.weight", "model.visual.blocks.25.norm2.weight", "model.visual.blocks.26.attn.proj.bias", "model.visual.blocks.26.attn.proj.weight", "model.visual.blocks.26.attn.qkv.bias", "model.visual.blocks.26.attn.qkv.weight", "model.visual.blocks.26.mlp.down_proj.bias", "model.visual.blocks.26.mlp.down_proj.weight", "model.visual.blocks.26.mlp.gate_proj.bias", "model.visual.blocks.26.mlp.gate_proj.weight", "model.visual.blocks.26.mlp.up_proj.bias", "model.visual.blocks.26.mlp.up_proj.weight", "model.visual.blocks.26.norm1.weight", "model.visual.blocks.26.norm2.weight", "model.visual.blocks.27.attn.proj.bias", "model.visual.blocks.27.attn.proj.weight", "model.visual.blocks.27.attn.qkv.bias", "model.visual.blocks.27.attn.qkv.weight", "model.visual.blocks.27.mlp.down_proj.bias", "model.visual.blocks.27.mlp.down_proj.weight", "model.visual.blocks.27.mlp.gate_proj.bias", "model.visual.blocks.27.mlp.gate_proj.weight", "model.visual.blocks.27.mlp.up_proj.bias", "model.visual.blocks.27.mlp.up_proj.weight", "model.visual.blocks.27.norm1.weight", "model.visual.blocks.27.norm2.weight", "model.visual.blocks.28.attn.proj.bias", "model.visual.blocks.28.attn.proj.weight", "model.visual.blocks.28.attn.qkv.bias", "model.visual.blocks.28.attn.qkv.weight", "model.visual.blocks.28.mlp.down_proj.bias", "model.visual.blocks.28.mlp.down_proj.weight", "model.visual.blocks.28.mlp.gate_proj.bias", "model.visual.blocks.28.mlp.gate_proj.weight", "model.visual.blocks.28.mlp.up_proj.bias", "model.visual.blocks.28.mlp.up_proj.weight", "model.visual.blocks.28.norm1.weight", "model.visual.blocks.28.norm2.weight", "model.visual.blocks.29.attn.proj.bias", "model.visual.blocks.29.attn.proj.weight", "model.visual.blocks.29.attn.qkv.bias", "model.visual.blocks.29.attn.qkv.weight", "model.visual.blocks.29.mlp.down_proj.bias", "model.visual.blocks.29.mlp.down_proj.weight", "model.visual.blocks.29.mlp.gate_proj.bias", "model.visual.blocks.29.mlp.gate_proj.weight", "model.visual.blocks.29.mlp.up_proj.bias", "model.visual.blocks.29.mlp.up_proj.weight", "model.visual.blocks.29.norm1.weight", "model.visual.blocks.29.norm2.weight", "model.visual.blocks.3.attn.proj.bias", "model.visual.blocks.3.attn.proj.weight", "model.visual.blocks.3.attn.qkv.bias", "model.visual.blocks.3.attn.qkv.weight", "model.visual.blocks.3.mlp.down_proj.bias", "model.visual.blocks.3.mlp.down_proj.weight", "model.visual.blocks.3.mlp.gate_proj.bias", "model.visual.blocks.3.mlp.gate_proj.weight", "model.visual.blocks.3.mlp.up_proj.bias", "model.visual.blocks.3.mlp.up_proj.weight", "model.visual.blocks.3.norm1.weight", "model.visual.blocks.3.norm2.weight", "model.visual.blocks.30.attn.proj.bias", "model.visual.blocks.30.attn.proj.weight", "model.visual.blocks.30.attn.qkv.bias", "model.visual.blocks.30.attn.qkv.weight", "model.visual.blocks.30.mlp.down_proj.bias", "model.visual.blocks.30.mlp.down_proj.weight", "model.visual.blocks.30.mlp.gate_proj.bias", "model.visual.blocks.30.mlp.gate_proj.weight", "model.visual.blocks.30.mlp.up_proj.bias", "model.visual.blocks.30.mlp.up_proj.weight", "model.visual.blocks.30.norm1.weight", "model.visual.blocks.30.norm2.weight", "model.visual.blocks.31.attn.proj.bias", "model.visual.blocks.31.attn.proj.weight", "model.visual.blocks.31.attn.qkv.bias", "model.visual.blocks.31.attn.qkv.weight", "model.visual.blocks.31.mlp.down_proj.bias", "model.visual.blocks.31.mlp.down_proj.weight", "model.visual.blocks.31.mlp.gate_proj.bias", "model.visual.blocks.31.mlp.gate_proj.weight", "model.visual.blocks.31.mlp.up_proj.bias", "model.visual.blocks.31.mlp.up_proj.weight", "model.visual.blocks.31.norm1.weight", "model.visual.blocks.31.norm2.weight", "model.visual.blocks.4.attn.proj.bias", "model.visual.blocks.4.attn.proj.weight", "model.visual.blocks.4.attn.qkv.bias", "model.visual.blocks.4.attn.qkv.weight", "model.visual.blocks.4.mlp.down_proj.bias", "model.visual.blocks.4.mlp.down_proj.weight", "model.visual.blocks.4.mlp.gate_proj.bias", "model.visual.blocks.4.mlp.gate_proj.weight", "model.visual.blocks.4.mlp.up_proj.bias", "model.visual.blocks.4.mlp.up_proj.weight", "model.visual.blocks.4.norm1.weight", "model.visual.blocks.4.norm2.weight", "model.visual.blocks.5.attn.proj.bias", "model.visual.blocks.5.attn.proj.weight", "model.visual.blocks.5.attn.qkv.bias", "model.visual.blocks.5.attn.qkv.weight", "model.visual.blocks.5.mlp.down_proj.bias", "model.visual.blocks.5.mlp.down_proj.weight", "model.visual.blocks.5.mlp.gate_proj.bias", "model.visual.blocks.5.mlp.gate_proj.weight", "model.visual.blocks.5.mlp.up_proj.bias", "model.visual.blocks.5.mlp.up_proj.weight", "model.visual.blocks.5.norm1.weight", "model.visual.blocks.5.norm2.weight", "model.visual.blocks.6.attn.proj.bias", "model.visual.blocks.6.attn.proj.weight", "model.visual.blocks.6.attn.qkv.bias", "model.visual.blocks.6.attn.qkv.weight", "model.visual.blocks.6.mlp.down_proj.bias", "model.visual.blocks.6.mlp.down_proj.weight", "model.visual.blocks.6.mlp.gate_proj.bias", "model.visual.blocks.6.mlp.gate_proj.weight", "model.visual.blocks.6.mlp.up_proj.bias", "model.visual.blocks.6.mlp.up_proj.weight", "model.visual.blocks.6.norm1.weight", "model.visual.blocks.6.norm2.weight", "model.visual.blocks.7.attn.proj.bias", "model.visual.blocks.7.attn.proj.weight", "model.visual.blocks.7.attn.qkv.bias", "model.visual.blocks.7.attn.qkv.weight", "model.visual.blocks.7.mlp.down_proj.bias", "model.visual.blocks.7.mlp.down_proj.weight", "model.visual.blocks.7.mlp.gate_proj.bias", "model.visual.blocks.7.mlp.gate_proj.weight", "model.visual.blocks.7.mlp.up_proj.bias", "model.visual.blocks.7.mlp.up_proj.weight", "model.visual.blocks.7.norm1.weight", "model.visual.blocks.7.norm2.weight", "model.visual.blocks.8.attn.proj.bias", "model.visual.blocks.8.attn.proj.weight", "model.visual.blocks.8.attn.qkv.bias", "model.visual.blocks.8.attn.qkv.weight", "model.visual.blocks.8.mlp.down_proj.bias", "model.visual.blocks.8.mlp.down_proj.weight", "model.visual.blocks.8.mlp.gate_proj.bias", "model.visual.blocks.8.mlp.gate_proj.weight", "model.visual.blocks.8.mlp.up_proj.bias", "model.visual.blocks.8.mlp.up_proj.weight", "model.visual.blocks.8.norm1.weight", "model.visual.blocks.8.norm2.weight", "model.visual.blocks.9.attn.proj.bias", "model.visual.blocks.9.attn.proj.weight", "model.visual.blocks.9.attn.qkv.bias", "model.visual.blocks.9.attn.qkv.weight", "model.visual.blocks.9.mlp.down_proj.bias", "model.visual.blocks.9.mlp.down_proj.weight", "model.visual.blocks.9.mlp.gate_proj.bias", "model.visual.blocks.9.mlp.gate_proj.weight", "model.visual.blocks.9.mlp.up_proj.bias", "model.visual.blocks.9.mlp.up_proj.weight", "model.visual.blocks.9.norm1.weight", "model.visual.blocks.9.norm2.weight", "model.visual.merger.ln_q.weight", "model.visual.merger.mlp.0.bias", "model.visual.merger.mlp.0.weight", "model.visual.merger.mlp.2.bias", "model.visual.merger.mlp.2.weight", "model.visual.patch_embed.proj.weight", "model.language_model.layers.10.input_layernorm.weight", "model.language_model.layers.10.mlp.down_proj.weight", "model.language_model.layers.10.mlp.gate_proj.weight", "model.language_model.layers.10.mlp.up_proj.weight", "model.language_model.layers.10.post_attention_layernorm.weight", "model.language_model.layers.10.self_attn.k_proj.bias", "model.language_model.layers.10.self_attn.k_proj.weight", "model.language_model.layers.10.self_attn.o_proj.weight", "model.language_model.layers.10.self_attn.q_proj.bias", "model.language_model.layers.10.self_attn.q_proj.weight", "model.language_model.layers.10.self_attn.v_proj.bias", "model.language_model.layers.10.self_attn.v_proj.weight", "model.language_model.layers.11.input_layernorm.weight", "model.language_model.layers.11.mlp.down_proj.weight", "model.language_model.layers.11.mlp.gate_proj.weight", "model.language_model.layers.11.mlp.up_proj.weight", "model.language_model.layers.11.post_attention_layernorm.weight", "model.language_model.layers.11.self_attn.k_proj.bias", "model.language_model.layers.11.self_attn.k_proj.weight", "model.language_model.layers.11.self_attn.o_proj.weight", "model.language_model.layers.11.self_attn.q_proj.bias", "model.language_model.layers.11.self_attn.q_proj.weight", "model.language_model.layers.11.self_attn.v_proj.bias", "model.language_model.layers.11.self_attn.v_proj.weight", "model.language_model.layers.12.input_layernorm.weight", "model.language_model.layers.12.mlp.down_proj.weight", "model.language_model.layers.12.mlp.gate_proj.weight", "model.language_model.layers.12.mlp.up_proj.weight", "model.language_model.layers.12.post_attention_layernorm.weight", "model.language_model.layers.12.self_attn.k_proj.bias", "model.language_model.layers.12.self_attn.k_proj.weight", "model.language_model.layers.12.self_attn.o_proj.weight", "model.language_model.layers.12.self_attn.q_proj.bias", "model.language_model.layers.12.self_attn.q_proj.weight", "model.language_model.layers.12.self_attn.v_proj.bias", "model.language_model.layers.12.self_attn.v_proj.weight", "model.language_model.layers.13.input_layernorm.weight", "model.language_model.layers.13.mlp.down_proj.weight", "model.language_model.layers.13.mlp.gate_proj.weight", "model.language_model.layers.13.mlp.up_proj.weight", "model.language_model.layers.13.post_attention_layernorm.weight", "model.language_model.layers.13.self_attn.k_proj.bias", "model.language_model.layers.13.self_attn.k_proj.weight", "model.language_model.layers.13.self_attn.o_proj.weight", "model.language_model.layers.13.self_attn.q_proj.bias", "model.language_model.layers.13.self_attn.q_proj.weight", "model.language_model.layers.13.self_attn.v_proj.bias", "model.language_model.layers.13.self_attn.v_proj.weight", "model.language_model.layers.14.input_layernorm.weight", "model.language_model.layers.14.mlp.down_proj.weight", "model.language_model.layers.14.mlp.gate_proj.weight", "model.language_model.layers.14.mlp.up_proj.weight", "model.language_model.layers.14.post_attention_layernorm.weight", "model.language_model.layers.14.self_attn.k_proj.bias", "model.language_model.layers.14.self_attn.k_proj.weight", "model.language_model.layers.14.self_attn.o_proj.weight", "model.language_model.layers.14.self_attn.q_proj.bias", "model.language_model.layers.14.self_attn.q_proj.weight", "model.language_model.layers.14.self_attn.v_proj.bias", "model.language_model.layers.14.self_attn.v_proj.weight", "model.language_model.layers.15.input_layernorm.weight", "model.language_model.layers.15.mlp.down_proj.weight", "model.language_model.layers.15.mlp.gate_proj.weight", "model.language_model.layers.15.mlp.up_proj.weight", "model.language_model.layers.15.post_attention_layernorm.weight", "model.language_model.layers.15.self_attn.k_proj.bias", "model.language_model.layers.15.self_attn.k_proj.weight", "model.language_model.layers.15.self_attn.o_proj.weight", "model.language_model.layers.15.self_attn.q_proj.bias", "model.language_model.layers.15.self_attn.q_proj.weight", "model.language_model.layers.15.self_attn.v_proj.bias", "model.language_model.layers.15.self_attn.v_proj.weight", "model.language_model.layers.16.self_attn.k_proj.bias", "model.language_model.layers.16.self_attn.k_proj.weight", "model.language_model.layers.16.self_attn.o_proj.weight", "model.language_model.layers.16.self_attn.q_proj.bias", "model.language_model.layers.16.self_attn.q_proj.weight", "model.language_model.layers.16.self_attn.v_proj.bias", "model.language_model.layers.16.self_attn.v_proj.weight", "model.language_model.layers.5.input_layernorm.weight", "model.language_model.layers.5.mlp.down_proj.weight", "model.language_model.layers.5.mlp.up_proj.weight", "model.language_model.layers.5.post_attention_layernorm.weight", "model.language_model.layers.6.input_layernorm.weight", "model.language_model.layers.6.mlp.down_proj.weight", "model.language_model.layers.6.mlp.gate_proj.weight", "model.language_model.layers.6.mlp.up_proj.weight", "model.language_model.layers.6.post_attention_layernorm.weight", "model.language_model.layers.6.self_attn.k_proj.bias", "model.language_model.layers.6.self_attn.k_proj.weight", "model.language_model.layers.6.self_attn.o_proj.weight", "model.language_model.layers.6.self_attn.q_proj.bias", "model.language_model.layers.6.self_attn.q_proj.weight", "model.language_model.layers.6.self_attn.v_proj.bias", "model.language_model.layers.6.self_attn.v_proj.weight", "model.language_model.layers.7.input_layernorm.weight", "model.language_model.layers.7.mlp.down_proj.weight", "model.language_model.layers.7.mlp.gate_proj.weight", "model.language_model.layers.7.mlp.up_proj.weight", "model.language_model.layers.7.post_attention_layernorm.weight", "model.language_model.layers.7.self_attn.k_proj.bias", "model.language_model.layers.7.self_attn.k_proj.weight", "model.language_model.layers.7.self_attn.o_proj.weight", "model.language_model.layers.7.self_attn.q_proj.bias", "model.language_model.layers.7.self_attn.q_proj.weight", "model.language_model.layers.7.self_attn.v_proj.bias", "model.language_model.layers.7.self_attn.v_proj.weight", "model.language_model.layers.8.input_layernorm.weight", "model.language_model.layers.8.mlp.down_proj.weight", "model.language_model.layers.8.mlp.gate_proj.weight", "model.language_model.layers.8.mlp.up_proj.weight", "model.language_model.layers.8.post_attention_layernorm.weight", "model.language_model.layers.8.self_attn.k_proj.bias", "model.language_model.layers.8.self_attn.k_proj.weight", "model.language_model.layers.8.self_attn.o_proj.weight", "model.language_model.layers.8.self_attn.q_proj.bias", "model.language_model.layers.8.self_attn.q_proj.weight", "model.language_model.layers.8.self_attn.v_proj.bias", "model.language_model.layers.8.self_attn.v_proj.weight", "model.language_model.layers.9.input_layernorm.weight", "model.language_model.layers.9.mlp.down_proj.weight", "model.language_model.layers.9.mlp.gate_proj.weight", "model.language_model.layers.9.mlp.up_proj.weight", "model.language_model.layers.9.post_attention_layernorm.weight", "model.language_model.layers.9.self_attn.k_proj.bias", "model.language_model.layers.9.self_attn.k_proj.weight", "model.language_model.layers.9.self_attn.o_proj.weight", "model.language_model.layers.9.self_attn.q_proj.bias", "model.language_model.layers.9.self_attn.q_proj.weight", "model.language_model.layers.9.self_attn.v_proj.bias", "model.language_model.layers.9.self_attn.v_proj.weight", "model.language_model.layers.16.input_layernorm.weight", "model.language_model.layers.16.mlp.down_proj.weight", "model.language_model.layers.16.mlp.gate_proj.weight", "model.language_model.layers.16.mlp.up_proj.weight", "model.language_model.layers.16.post_attention_layernorm.weight", "model.language_model.layers.17.input_layernorm.weight", "model.language_model.layers.17.mlp.down_proj.weight", "model.language_model.layers.17.mlp.gate_proj.weight", "model.language_model.layers.17.mlp.up_proj.weight", "model.language_model.layers.17.post_attention_layernorm.weight", "model.language_model.layers.17.self_attn.k_proj.bias", "model.language_model.layers.17.self_attn.k_proj.weight", "model.language_model.layers.17.self_attn.o_proj.weight", "model.language_model.layers.17.self_attn.q_proj.bias", "model.language_model.layers.17.self_attn.q_proj.weight", "model.language_model.layers.17.self_attn.v_proj.bias", "model.language_model.layers.17.self_attn.v_proj.weight", "model.language_model.layers.18.input_layernorm.weight", "model.language_model.layers.18.mlp.down_proj.weight", "model.language_model.layers.18.mlp.gate_proj.weight", "model.language_model.layers.18.mlp.up_proj.weight", "model.language_model.layers.18.post_attention_layernorm.weight", "model.language_model.layers.18.self_attn.k_proj.bias", "model.language_model.layers.18.self_attn.k_proj.weight", "model.language_model.layers.18.self_attn.o_proj.weight", "model.language_model.layers.18.self_attn.q_proj.bias", "model.language_model.layers.18.self_attn.q_proj.weight", "model.language_model.layers.18.self_attn.v_proj.bias", "model.language_model.layers.18.self_attn.v_proj.weight", "model.language_model.layers.19.input_layernorm.weight", "model.language_model.layers.19.mlp.down_proj.weight", "model.language_model.layers.19.mlp.gate_proj.weight", "model.language_model.layers.19.mlp.up_proj.weight", "model.language_model.layers.19.post_attention_layernorm.weight", "model.language_model.layers.19.self_attn.k_proj.bias", "model.language_model.layers.19.self_attn.k_proj.weight", "model.language_model.layers.19.self_attn.o_proj.weight", "model.language_model.layers.19.self_attn.q_proj.bias", "model.language_model.layers.19.self_attn.q_proj.weight", "model.language_model.layers.19.self_attn.v_proj.bias", "model.language_model.layers.19.self_attn.v_proj.weight", "model.language_model.layers.20.input_layernorm.weight", "model.language_model.layers.20.mlp.down_proj.weight", "model.language_model.layers.20.mlp.gate_proj.weight", "model.language_model.layers.20.mlp.up_proj.weight", "model.language_model.layers.20.post_attention_layernorm.weight", "model.language_model.layers.20.self_attn.k_proj.bias", "model.language_model.layers.20.self_attn.k_proj.weight", "model.language_model.layers.20.self_attn.o_proj.weight", "model.language_model.layers.20.self_attn.q_proj.bias", "model.language_model.layers.20.self_attn.q_proj.weight", "model.language_model.layers.20.self_attn.v_proj.bias", "model.language_model.layers.20.self_attn.v_proj.weight", "model.language_model.layers.21.input_layernorm.weight", "model.language_model.layers.21.mlp.down_proj.weight", "model.language_model.layers.21.mlp.gate_proj.weight", "model.language_model.layers.21.mlp.up_proj.weight", "model.language_model.layers.21.post_attention_layernorm.weight", "model.language_model.layers.21.self_attn.k_proj.bias", "model.language_model.layers.21.self_attn.k_proj.weight", "model.language_model.layers.21.self_attn.o_proj.weight", "model.language_model.layers.21.self_attn.q_proj.bias", "model.language_model.layers.21.self_attn.q_proj.weight", "model.language_model.layers.21.self_attn.v_proj.bias", "model.language_model.layers.21.self_attn.v_proj.weight", "model.language_model.layers.22.input_layernorm.weight", "model.language_model.layers.22.mlp.down_proj.weight", "model.language_model.layers.22.mlp.gate_proj.weight", "model.language_model.layers.22.mlp.up_proj.weight", "model.language_model.layers.22.post_attention_layernorm.weight", "model.language_model.layers.22.self_attn.k_proj.bias", "model.language_model.layers.22.self_attn.k_proj.weight", "model.language_model.layers.22.self_attn.o_proj.weight", "model.language_model.layers.22.self_attn.q_proj.bias", "model.language_model.layers.22.self_attn.q_proj.weight", "model.language_model.layers.22.self_attn.v_proj.bias", "model.language_model.layers.22.self_attn.v_proj.weight", "model.language_model.layers.23.input_layernorm.weight", "model.language_model.layers.23.mlp.down_proj.weight", "model.language_model.layers.23.mlp.gate_proj.weight", "model.language_model.layers.23.mlp.up_proj.weight", "model.language_model.layers.23.post_attention_layernorm.weight", "model.language_model.layers.23.self_attn.k_proj.bias", "model.language_model.layers.23.self_attn.k_proj.weight", "model.language_model.layers.23.self_attn.o_proj.weight", "model.language_model.layers.23.self_attn.q_proj.bias", "model.language_model.layers.23.self_attn.q_proj.weight", "model.language_model.layers.23.self_attn.v_proj.bias", "model.language_model.layers.23.self_attn.v_proj.weight", "model.language_model.layers.24.input_layernorm.weight", "model.language_model.layers.24.mlp.down_proj.weight", "model.language_model.layers.24.mlp.gate_proj.weight", "model.language_model.layers.24.mlp.up_proj.weight", "model.language_model.layers.24.post_attention_layernorm.weight", "model.language_model.layers.24.self_attn.k_proj.bias", "model.language_model.layers.24.self_attn.k_proj.weight", "model.language_model.layers.24.self_attn.o_proj.weight", "model.language_model.layers.24.self_attn.q_proj.bias", "model.language_model.layers.24.self_attn.q_proj.weight", "model.language_model.layers.24.self_attn.v_proj.bias", "model.language_model.layers.24.self_attn.v_proj.weight", "model.language_model.layers.25.input_layernorm.weight", "model.language_model.layers.25.mlp.down_proj.weight", "model.language_model.layers.25.mlp.gate_proj.weight", "model.language_model.layers.25.mlp.up_proj.weight", "model.language_model.layers.25.post_attention_layernorm.weight", "model.language_model.layers.25.self_attn.k_proj.bias", "model.language_model.layers.25.self_attn.k_proj.weight", "model.language_model.layers.25.self_attn.o_proj.weight", "model.language_model.layers.25.self_attn.q_proj.bias", "model.language_model.layers.25.self_attn.q_proj.weight", "model.language_model.layers.25.self_attn.v_proj.bias", "model.language_model.layers.25.self_attn.v_proj.weight", "model.language_model.layers.26.mlp.gate_proj.weight", "model.language_model.layers.26.mlp.up_proj.weight", "model.language_model.layers.26.self_attn.k_proj.bias", "model.language_model.layers.26.self_attn.k_proj.weight", "model.language_model.layers.26.self_attn.o_proj.weight", "model.language_model.layers.26.self_attn.q_proj.bias", "model.language_model.layers.26.self_attn.q_proj.weight", "model.language_model.layers.26.self_attn.v_proj.bias", "model.language_model.layers.26.self_attn.v_proj.weight", "model.language_model.layers.26.input_layernorm.weight", "model.language_model.layers.26.mlp.down_proj.weight", "model.language_model.layers.26.post_attention_layernorm.weight", "model.language_model.layers.27.input_layernorm.weight", "model.language_model.layers.27.mlp.down_proj.weight", "model.language_model.layers.27.mlp.gate_proj.weight", "model.language_model.layers.27.mlp.up_proj.weight", "model.language_model.layers.27.post_attention_layernorm.weight", "model.language_model.layers.27.self_attn.k_proj.bias", "model.language_model.layers.27.self_attn.k_proj.weight", "model.language_model.layers.27.self_attn.o_proj.weight", "model.language_model.layers.27.self_attn.q_proj.bias", "model.language_model.layers.27.self_attn.q_proj.weight", "model.language_model.layers.27.self_attn.v_proj.bias", "model.language_model.layers.27.self_attn.v_proj.weight", "model.language_model.norm.weight". (qwen_image)[DiffSynth-Studio]$
