Initial commit

config.json

@@ -0,0 +1,138 @@
+{
+  "architectures": [
+    "ARCHunyuanVideoForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "openai/whisper-large-v3",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "apply_spec_augment": false,
+    "attention_dropout": 0.0,
+    "begin_suppress_tokens": [
+      220,
+      50257
+    ],
+    "bos_token_id": 50257,
+    "classifier_proj_size": 256,
+    "d_model": 1280,
+    "decoder_attention_heads": 20,
+    "decoder_ffn_dim": 5120,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 32,
+    "decoder_start_token_id": 50258,
+    "dropout": 0.0,
+    "encoder_attention_heads": 20,
+    "encoder_ffn_dim": 5120,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 32,
+    "eos_token_id": 50257,
+    "init_std": 0.02,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.05,
+    "max_length": 448,
+    "max_source_positions": 1500,
+    "max_target_positions": 448,
+    "median_filter_width": 7,
+    "model_type": "arc_hunyuan_video_audio",
+    "num_hidden_layers": 32,
+    "num_mel_bins": 128,
+    "scale_embedding": false,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 51866
+  },
+  "max_num_frame": 150,
+  "model_type": "arc_hunyuan_video",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_head_dim": 128,
+    "bos_token_id": 127959,
+    "eod_token_id": 127957,
+    "eos_token_id": 127960,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "im_end_id": 127963,
+    "im_newline_id": 127964,
+    "im_start_id": 127962,
+    "image_token_id": 127968,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_causal": true,
+    "max_position_embeddings": 1024,
+    "mlp_bias": false,
+    "model_type": "arc_hunyuan_video_text",
+    "norm_type": "hf_rms",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_media_embeds": 257,
+    "pad_token_id": 127961,
+    "position_embedding_xdrope": true,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "alpha": 1000.0,
+      "beta_fast": 32,
+      "beta_slow": 1,
+      "factor": 1.0,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "type": "dynamic"
+    },
+    "rope_theta": 10000.0,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "use_rotary_pos_emb": true,
+    "vocab_size": 128256,
+    "xdrope_section": [
+      0.25,
+      0.25,
+      0.25,
+      0.25
+    ]
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0.dev0",
+  "vision_config": {
+    "anyres_pooling_size": 2,
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "attention_head_dim": 72,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "force_image_size": 640,
+    "hidden_act": "gelu",
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "is_causal": false,
+    "layer_norm_eps": 1e-05,
+    "max_image_size": 2048,
+    "max_vit_seq_len": 1600,
+    "mlp_bias": true,
+    "model_type": "arc_hunyuan_video_vision",
+    "norm_type": "torch_nn",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "pad_token_id": 0,
+    "patch_size": 16,
+    "position_embedding_xdrope": true,
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "bfloat16",
+    "use_qk_norm": false,
+    "use_rotary_pos_emb": false,
+    "xdrope_section": [
+      0.25,
+      0.25,
+      0.25,
+      0.25
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 127959,
+  "chat_format": "chatml",
+  "eos_token_id": 127957,
+  "max_new_tokens": 512,
+  "max_window_size": 6144,
+  "pad_token_id": 127961,
+  "repetition_penalty": 1.1,
+  "transformers_version": "4.54.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda3b9a5ca10c7236485f449dad35510648a4b0dc6eb2abbc0dfe17935b0049a
+size 4976703472

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd42f4a62dd64fec41ee80e2ac469ec4262f838b839b964a704dcdf54430e2b
+size 4882368512

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb4743c0437e95a33ed6484276521c8018eec176d4c0bd9724e1ebaa1010252
+size 4798481400

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3054c0562172cf821ac0814c5d40f0e9070a3aa45e62b4a1d43cc78cca31ed
+size 2613316976

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "ARCHunyuanVideoProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "eos_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "added_tokens_decoder": {},
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "processor_class": "ARCHunyuanVideoProcessor",
+  "tokenizer_class": "ARCHunyuanVideoTokenizer"
+}