generative-models icon indicating copy to clipboard operation
generative-models copied to clipboard

SDXL-base1.0 uses CLIP-ViT-H-14-laion2B-s32B-b79K

Open mocha1908 opened this issue 1 year ago • 0 comments

checkpoints: sd_xl_base_1.0.safetensors laion: CLIP-ViT-H-14-laion2B-s32B-b79K Why do the following errors occur:

Traceback (most recent call last): File "/home/anaconda3/envs/SDXL/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 88, in exec_func_with_error_handling result = func() File "/home/anaconda3/envs/SDXL/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 579, in code_to_exec exec(code, module.dict) File "/home/stable_diffusion/generative-models/sampling.py", line 291, in state = init_st(version_dict, load_filter=True, device=device) File "/home/anaconda3/envs/SDXL/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 218, in call return self._get_or_create_cached_value(args, kwargs, spinner_message) File "/home/anaconda3/envs/SDXL/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 260, in _get_or_create_cached_value return self._handle_cache_miss(cache, value_key, func_args, func_kwargs) File "/home/anaconda3/envs/SDXL/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 318, in _handle_cache_miss computed_value = self._info.func(*func_args, **func_kwargs) File "/home/stable_diffusion/generative-models/scripts/demo/streamlit_helpers.py", line 52, in init_st model, msg = load_model_from_config(config, ckpt if load_ckpt else None, device=device) File "/home/stable_diffusion/generative-models/scripts/demo/streamlit_helpers.py", line 110, in load_model_from_config m, u = model.load_state_dict(sd, strict=False) File "/home/anaconda3/envs/SDXL/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2041, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for DiffusionEngine: size mismatch for conditioner.embedders.1.model.positional_embedding: copying a param with shape torch.Size([77, 1280]) from checkpoint, the shape in current model is torch.Size([77, 1024]). size mismatch for conditioner.embedders.1.model.text_projection: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.0.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.1.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.2.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.3.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.4.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.5.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.6.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.7.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.8.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.9.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.10.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.11.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.12.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.13.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.14.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.15.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.16.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.17.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.18.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.19.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.20.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.21.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.22.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.ln_1.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.ln_1.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.attn.in_proj_weight: copying a param with shape torch.Size([3840, 1280]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.attn.in_proj_bias: copying a param with shape torch.Size([3840]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.attn.out_proj.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.attn.out_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.ln_2.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.ln_2.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.mlp.c_fc.weight: copying a param with shape torch.Size([5120, 1280]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.mlp.c_fc.bias: copying a param with shape torch.Size([5120]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.mlp.c_proj.weight: copying a param with shape torch.Size([1280, 5120]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for conditioner.embedders.1.model.transformer.resblocks.23.mlp.c_proj.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.token_embedding.weight: copying a param with shape torch.Size([49408, 1280]) from checkpoint, the shape in current model is torch.Size([49408, 1024]). size mismatch for conditioner.embedders.1.model.ln_final.weight: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for conditioner.embedders.1.model.ln_final.bias: copying a param with shape torch.Size([1280]) from checkpoint, the shape in current model is torch.Size([1024]).

mocha1908 avatar Feb 12 '25 06:02 mocha1908