End of training

lr_scheduler/lr_scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9a5d647349c541df37221f857f1528d69a64ee8921808d7169158f833bb344
+size 1076

model_index.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "UTTIPipeline",
+  "_diffusers_version": "0.25.0.dev0",
+  "scheduler": [
+    "sde_torch_param",
+    "TorchSDE_PARAM"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ]
+}

optimizer/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f34df97eb513092c462fa74b65f962ec250c7519858727ecac8ddd886ee985
+size 6876705882

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "TorchSDE_PARAM",
+  "_config_class_name": "SDEParameterizedMaxNoiseBaseLineConfig",
+  "_diffusers_version": "0.25.0.dev0",
+  "data_dimension": 3072
+}

scheduler/scheduler_config.py

@@ -0,0 +1,44 @@
+import jax.numpy as jnp
+import jax
+import torch
+from dataclasses import dataclass
+import sympy
+import sympy as sp
+from sympy import Matrix, Symbol
+import math
+from sde_redefined_param import SDEDimension
+@dataclass
+class SDEParameterizedMaxNoiseBaseLineConfig:
+    name = "Custom"
+    variable = Symbol('t', nonnegative=True, real=True)
+
+    drift_dimension = SDEDimension.SCALAR 
+    diffusion_dimension = SDEDimension.SCALAR
+    diffusion_matrix_dimension = SDEDimension.SCALAR 
+
+    # TODO (KLAUS): HANDLE THE PARAMETERS BEING Ø
+    drift_parameters = Matrix([sympy.symbols("f1", real=True)])
+    diffusion_parameters = Matrix([sympy.symbols("sigma_max", real=True, nonzero=True)])
+    
+    drift = 0
+
+    sigma_min = 0.002 
+    sigma_max = sympy.Abs(diffusion_parameters[0]) #80
+    diffusion = sigma_min * (sigma_max/sigma_min)**variable * sympy.sqrt(2 * sympy.Abs(sympy.log(sigma_max/sigma_min))) 
+
+    # TODO (KLAUS) : in the SDE SAMPLING CHANGING Q impacts how we sample z ~ N(0, Q*(delta t))
+    diffusion_matrix = 1 
+
+    initial_variable_value = 0
+    max_variable_value = 1 # math.inf
+    min_sample_value = 0
+
+    module = 'jax'
+
+    drift_integral_form=False
+    diffusion_integral_form=False
+    diffusion_integral_decomposition = 'cholesky' # ldl
+
+    non_symbolic_parameters = {'diffusion': torch.tensor([80.])}
+
+    target = "epsilon" # x0

scheduler/sdeparameters.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde7ae00f1831d4837f33ba5607db8775b862e55d7febdb1941f11f95049439f
+size 136

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "AltLuv/pokemon-test-tti",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 3,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 3,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 32,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c458158975159865576d8a4880325fd28ebdb8940273294b273fe2cfb8917d7
+size 3438144492