Upload folder using huggingface_hub

2_1/decoder_fp16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6eaaee7d104073cfca18fd0318cba0c23e96634d83e15b91669e04d3854c6
+size 2683523457

2_1/movq_final.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2ded4afb21c1a90d106a6aa4d37be7040fe6bce87f08e12bad2ea83d892b9a
+size 271481827

2_1/prior_fp16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028e6618d320f7f4471daeeb54d47784a053a3d6b7dad377bc4f3c817c8564e3
+size 2044156871

2_1/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.17.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

2_1/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad09a3a1ccf35d93c95c08686506fc59c966d77ac1f5833413366c4d327cb2d
+size 2242872365

2_1/text_encoder/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

2_1/text_encoder/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

2_1/text_encoder/tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}

SAM/sam_vit_b_01ec64.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2df62732614e57411cdcf32a23ffdf28910380d03139ee0f4fcbe91eb8c912
+size 375042383

SAM/sam_vit_h_4b8939.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bf3b02f3ebf1267aba913ff637d9a2d5c33d3173bb679e46d9f338c26f262e
+size 2564550879

SAM/sam_vit_l_0b3195.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adcc4315b642a4d2101128f611684e8734c41232a17c648ed1693702a49a622
+size 1249524607

checkpoints/model_large_caption.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d79b3b7c41478b5fe55c35b73ca6f3525a09708289371c6c0fac641e588287e
+size 1785411505

clip_cache/ViT-L-14.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cca3fd41ae0c99ba7e8951adf17d267cdb84cd88be6f7c2e0eca1737a03836
+size 932768134

clip_cache/ViT-L-14_openai_artists.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf73197c78825d443a3415f0df3e46d2068a77a874ca62eb575d39b02de76ad
+size 16174296

clip_cache/ViT-L-14_openai_flavors.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794576a1605913445f44c7d45d891ce171ef9b8c3e91beaf95a25a1afccb1580
+size 155090140

clip_cache/ViT-L-14_openai_mediums.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a18152cd3e3d72a4b30f2f6a99a9a0c65a2134bb11ddbd1b793038c067cf49
+size 146127

clip_cache/ViT-L-14_openai_movements.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4944e4aa89138c85fcaceecefd17be68239e2fd243c3336d502bc9d9dd1ead56
+size 307408

clip_cache/ViT-L-14_openai_negative.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c3820ad959eab90dcc98778c38f6e54c0fba98433ed2eafea0c6d1850b4d8c
+size 63184

clip_cache/ViT-L-14_openai_trendings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9e6bbc39318dd4bb40a5790d68faca785629068aaccd02bf2854c50bc47532
+size 110799

esrgan/RealESRGAN_x2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c830d067d54fc767b9543a8432f36d91bc2de313584e8bbfe4ac26a47339e899
+size 67061725

shap-e/ViT-L-14.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cca3fd41ae0c99ba7e8951adf17d267cdb84cd88be6f7c2e0eca1737a03836
+size 932768134

shap-e/diffusion_config.yaml

@@ -0,0 +1,3 @@
+mean_type: x_start
+schedule: exp
+timesteps: 1024

shap-e/image_cond.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8072c64bbbcf6910488814d212227de5db291780d4ea99c6152f9346cf12aa
+size 1263925407

shap-e/image_cond_config.yaml

@@ -0,0 +1,13 @@
+d_latent: 1048576
+inner:
+  cond_drop_prob: 0.1
+  heads: 8
+  init_scale: 0.25
+  layers: 24
+  name: CLIPImageGridPointDiffusionTransformer
+  pos_emb_init_scale: 0.05
+  time_token_cond: true
+  use_pos_emb: true
+  width: 1024
+latent_ctx: 1024
+name: SplitVectorDiffusion

shap-e/transmitter.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af02a0b85a8abdfb3919584b63c540ba175f6ad4790f574a7fef4617e5acdc3b
+size 1776048343

shap-e/transmitter_config.yaml

@@ -0,0 +1,80 @@
+encoder:
+  cross_attention_dataset: pcl_and_multiview_pcl
+  d_latent: 1024
+  data_ctx: 1024
+  fps_method: first
+  heads: 8
+  init_scale: 0.25
+  inner_batch_size:
+  - 16384
+  - 20
+  input_channels: 6
+  latent_bottleneck:
+    diffusion:
+      schedule: inv_parabola
+      schedule_args:
+        power: 5.0
+      timesteps: 1024
+    diffusion_prob: 0.1
+    name: clamp_diffusion_noise
+  layers: 12
+  max_depth: 9.0
+  max_unrolls: 1
+  min_unrolls: 1
+  name: PointCloudPerceiverChannelsEncoder
+  params_proj:
+    init_scale: 1.0
+    learned_scale: 0.0625
+    name: channels
+    use_ln: true
+  patch_size: 8
+  pointconv_hidden:
+  - 1024
+  - 1024
+  pointconv_padding_mode: circular
+  pointconv_patch_size: 8
+  pointconv_samples: 64
+  pointconv_stride: 4
+  pos_emb: nerf
+  use_depth: true
+  use_pointconv: true
+  width: 1024
+name: Transmitter
+renderer:
+  grid_size: 128
+  n_coarse_samples: 64
+  n_fine_samples: 128
+  name: NeRSTFRenderer
+  nerstf:
+    activation: swish
+    d_hidden: 256
+    density_activation: relu
+    init_scale: 0.25
+    initial_density_bias: 0.1
+    insert_direction_at: 4
+    meta_bias: false
+    meta_parameters: true
+    n_hidden_layers: 6
+    n_meta_layers: 4
+    name: MLPNeRSTFModel
+    posenc_version: nerf
+    separate_coarse_channels: true
+    separate_nerf_channels: true
+    trainable_meta: false
+  separate_shared_samples: true
+  void:
+    background:
+    - 0
+    - 0
+    - 0
+    name: VoidNeRFModel
+  volume:
+    bbox_max:
+    - 1.0
+    - 1.0
+    - 1.0
+    bbox_min:
+    - -1.0
+    - -1.0
+    - -1.0
+    name: BoundingBoxVolume