Update tiny models for Emu3ForConditionalGeneration

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,155 @@
+{
+  "architectures": [
+    "Emu3ForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_token_id": 3,
+  "model_type": "emu3",
+  "text_config": {
+    "attention_dropout": 0.1,
+    "bos_token_id": 151849,
+    "eos_token_id": 151850,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "max_position_embeddings": 512,
+    "model_type": "emu3_text_model",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 184622
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "vocabulary_map": {
+    "\u0000": 0,
+    "\u0001": 1,
+    "\u0002": 2,
+    "\u0017": 23,
+    "\u0018": 24,
+    "\u0019": 25,
+    "\u001a": 26,
+    "\u001b": 27,
+    "\u001c": 28,
+    "\u001d": 29,
+    "\u001e": 30,
+    "\u001f": 31,
+    " ": 32,
+    "!": 33,
+    "\"": 34,
+    "#": 35,
+    "$": 36,
+    "%": 37,
+    "&": 38,
+    "'": 39,
+    "(": 40,
+    ")": 41,
+    "*": 42,
+    "+": 43,
+    ",": 44,
+    "-": 45,
+    ".": 46,
+    "/": 47,
+    "0": 48,
+    "1": 49,
+    "2": 50,
+    "3": 51,
+    "4": 52,
+    "5": 53,
+    "6": 54,
+    "7": 55,
+    "8": 56,
+    "9": 57,
+    ":": 58,
+    ";": 59,
+    "<": 60,
+    "<image>": 3,
+    "<|extra_200|>": 4,
+    "<|visual token000005|>": 5,
+    "<|visual token000006|>": 6,
+    "<|visual token000007|>": 7,
+    "<|visual token000008|>": 8,
+    "<|visual token000009|>": 9,
+    "<|visual token000010|>": 10,
+    "<|visual token000011|>": 11,
+    "<|visual token000012|>": 12,
+    "<|visual token000013|>": 13,
+    "<|visual token000014|>": 14,
+    "<|visual token000015|>": 15,
+    "<|visual token000016|>": 16,
+    "<|visual token000017|>": 17,
+    "<|visual token000018|>": 18,
+    "<|visual token000019|>": 19,
+    "<|visual token000020|>": 20,
+    "<|visual token000021|>": 21,
+    "<|visual token000022|>": 22,
+    "=": 61,
+    ">": 62,
+    "?": 63,
+    "@": 64,
+    "A": 65,
+    "B": 66,
+    "C": 67,
+    "D": 68,
+    "E": 69,
+    "F": 70,
+    "G": 71,
+    "H": 72,
+    "I": 73,
+    "J": 74,
+    "K": 75,
+    "L": 76,
+    "M": 77,
+    "N": 78,
+    "O": 79,
+    "P": 80,
+    "Q": 81,
+    "R": 82,
+    "S": 83,
+    "T": 84,
+    "U": 85,
+    "V": 86,
+    "W": 87,
+    "X": 88,
+    "Y": 89,
+    "Z": 90,
+    "[": 91,
+    "\\": 92,
+    "]": 93,
+    "^": 94,
+    "_": 95,
+    "`": 96,
+    "a": 97,
+    "b": 98
+  },
+  "vq_config": {
+    "attention_dropout": 0.0,
+    "attn_resolutions": [],
+    "base_channels": 32,
+    "channel_multiplier": [
+      1,
+      2,
+      1
+    ],
+    "codebook_size": 20,
+    "double_latent": false,
+    "embed_dim": 4,
+    "hidden_size": 32,
+    "in_channels": 3,
+    "latent_channels": 4,
+    "model_type": "emu3_vqgan",
+    "num_attention_heads": 1,
+    "num_res_blocks": 2,
+    "out_channels": 3,
+    "temporal_downsample_factor": 1
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151849,
+  "eos_token_id": 151850,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 151643,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c43b5f8cf43257c541d9b0108c828be7f31eb91ed59594e34b1d180af44a8e
+size 50329812

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "BAAI/Emu3-VisionTokenizer--image_processing_emu3visionvq.Emu3VisionVQImageProcessor"
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Emu3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_pixels": 1048576,
+  "min_pixels": 262144,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 1048576,
+    "min_pixels": 262144
+  },
+  "spatial_factor": 8
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3168c45f8818df965a786164534cfce2dd99695cf7f3aca2168e90da4d1c843b
+size 19361077

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "boi_token": "<|image start|>",
+  "bos_token": "<|extra_203|>",
+  "clean_up_tokenization_spaces": false,
+  "eof_token": "<|extra_201|>",
+  "eoi_token": "<|image end|>",
+  "eos_token": "<|extra_204|>",
+  "errors": "replace",
+  "image_token": "<image>",
+  "image_wrapper_token": "<|image token|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<|image start|>",
+    "eof_token": "<|extra_201|>",
+    "eoi_token": "<|image end|>",
+    "image_token": "<image>",
+    "image_wrapper_token": "<|image token|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Emu3Processor",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}