Upload folder using huggingface_hub

.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
+text_tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "Cosmos3OmniDiffusersPipeline",
+  "_diffusers_version": "0.37.1",
+  "scheduler": [
+    "diffusers",
+    "UniPCMultistepScheduler"
+  ],
+  "text_tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "Cosmos3OmniTransformer"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan"
+  ],
+  "vision_encoder": [
+    "transformers",
+    "Qwen3VLVisionModel"
+  ],
+  "sound_tokenizer": [
+    "diffusers",
+    "Cosmos3AVAEAudioTokenizer"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "UniPCMultistepScheduler",
+  "_diffusers_version": "0.37.1",
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "beta_start": 0.0001,
+  "disable_corrector": [],
+  "dynamic_thresholding_ratio": 0.995,
+  "final_sigmas_type": "zero",
+  "flow_shift": 1.0,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "predict_x0": true,
+  "prediction_type": "flow_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "shift_terminal": null,
+  "sigma_max": 200.0,
+  "sigma_min": 0.147,
+  "solver_order": 2,
+  "solver_p": null,
+  "solver_type": "bh2",
+  "steps_offset": 0,
+  "thresholding": false,
+  "time_shift_type": "exponential",
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_flow_sigmas": true,
+  "use_karras_sigmas": true
+}

sound_tokenizer/config.json

@@ -0,0 +1,64 @@
+{
+    "model_type": "autoencoder_v2",
+    "sampling_rate": 48000,
+    "stereo": true,
+    "use_wav_as_input": true,
+    "normalize_volume": true,
+    "hop_size": 1920,
+    "input_channels": 1,
+    "enc_type": "spec_convnext",
+    "enc_dim": 192,
+    "enc_intermediate_dim": 768,
+    "enc_num_layers": 12,
+    "enc_num_blocks": 2,
+    "enc_n_fft": 64,
+    "enc_hop_length": 16,
+    "enc_latent_dim": 128,
+    "enc_c_mults": [
+        1,
+        2,
+        4
+    ],
+    "enc_strides": [
+        4,
+        5,
+        6
+    ],
+    "enc_identity_init": false,
+    "enc_use_snake": true,
+    "dec_type": "oobleck",
+    "dec_dim": 320,
+    "dec_c_mults": [
+        1,
+        2,
+        4,
+        8,
+        16
+    ],
+    "dec_strides": [
+        2,
+        4,
+        5,
+        6,
+        8
+    ],
+    "dec_use_snake": true,
+    "dec_final_tanh": false,
+    "dec_out_channels": 2,
+    "dec_anti_aliasing": false,
+    "dec_use_nearest_upsample": false,
+    "dec_use_tanh_at_final": false,
+    "bottleneck_type": "vae",
+    "bottleneck": {
+        "type": "vae"
+    },
+    "activation": "snakebeta",
+    "snake_logscale": true,
+    "anti_aliasing": false,
+    "use_cuda_kernel": false,
+    "causal": false,
+    "padding_mode": "zeros",
+    "vocoder_input_dim": 64,
+    "latent_mean": null,
+    "latent_std": null
+}

sound_tokenizer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4c61cde38acfb0cad9048a140c3533750277a8462b19dc08450d9fe1ad9879
+size 1892409600

text_tokenizer/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

text_tokenizer/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

text_tokenizer/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

text_tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

text_tokenizer/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,54 @@
+{
+  "_class_name": "Cosmos3OmniTransformer",
+  "_diffusers_version": "0.37.1",
+  "action_dim": 64,
+  "action_gen": true,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "base_fps": 24,
+  "dtype": "bfloat16",
+  "enable_fps_modulation": true,
+  "freeze_und": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "joint_attn_implementation": "two_way",
+  "latent_channel": 48,
+  "latent_patch_size": 2,
+  "max_action_dim": 64,
+  "max_position_embeddings": 262144,
+  "model_type": "qwen3_vl_text",
+  "num_attention_heads": 32,
+  "num_embodiment_domains": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "patch_latent_dim": 192,
+  "position_embedding_type": "unified_3d_mrope",
+  "qk_norm": false,
+  "qk_norm_for_diffusion": true,
+  "qk_norm_for_text": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      24,
+      20,
+      20
+    ],
+    "rope_type": "default"
+  },
+  "rope_theta": 5000000,
+  "sound_dim": 64,
+  "sound_gen": true,
+  "sound_latent_fps": 25,
+  "temporal_compression_factor_sound": 1,
+  "timestep_scale": 0.001,
+  "unified_3d_mrope_reset_spatial_ids": true,
+  "unified_3d_mrope_temporal_modality_margin": 15000,
+  "use_cache": true,
+  "use_moe": true,
+  "video_temporal_causal": false,
+  "vocab_size": 151936
+}

transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d836f8aca110a65017b0f420c62912ef0b5bc5c00e72ddb69be0643ee6c9aa4
+size 18952452192

vae/config.json

@@ -0,0 +1,129 @@
+{
+  "_class_name": "AutoencoderKLWan",
+  "_diffusers_version": "0.37.1",
+  "_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
+  "attn_scales": [],
+  "base_dim": 160,
+  "clip_output": false,
+  "decoder_base_dim": 256,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "in_channels": 12,
+  "is_residual": true,
+  "latents_mean": [
+    -0.2289,
+    -0.0052,
+    -0.1323,
+    -0.2339,
+    -0.2799,
+    0.0174,
+    0.1838,
+    0.1557,
+    -0.1382,
+    0.0542,
+    0.2813,
+    0.0891,
+    0.157,
+    -0.0098,
+    0.0375,
+    -0.1825,
+    -0.2246,
+    -0.1207,
+    -0.0698,
+    0.5109,
+    0.2665,
+    -0.2108,
+    -0.2158,
+    0.2502,
+    -0.2055,
+    -0.0322,
+    0.1109,
+    0.1567,
+    -0.0729,
+    0.0899,
+    -0.2799,
+    -0.123,
+    -0.0313,
+    -0.1649,
+    0.0117,
+    0.0723,
+    -0.2839,
+    -0.2083,
+    -0.052,
+    0.3748,
+    0.0152,
+    0.1957,
+    0.1433,
+    -0.2944,
+    0.3573,
+    -0.0548,
+    -0.1681,
+    -0.0667
+  ],
+  "latents_std": [
+    0.4765,
+    1.0364,
+    0.4514,
+    1.1677,
+    0.5313,
+    0.499,
+    0.4818,
+    0.5013,
+    0.8158,
+    1.0344,
+    0.5894,
+    1.0901,
+    0.6885,
+    0.6165,
+    0.8454,
+    0.4978,
+    0.5759,
+    0.3523,
+    0.7135,
+    0.6804,
+    0.5833,
+    1.4146,
+    0.8986,
+    0.5659,
+    0.7069,
+    0.5338,
+    0.4889,
+    0.4917,
+    0.4069,
+    0.4999,
+    0.6866,
+    0.4093,
+    0.5709,
+    0.6065,
+    0.6415,
+    0.4944,
+    0.5726,
+    1.2042,
+    0.5458,
+    1.6887,
+    0.3971,
+    1.06,
+    0.3943,
+    0.5537,
+    0.5444,
+    0.4089,
+    0.7468,
+    0.7744
+  ],
+  "num_res_blocks": 2,
+  "out_channels": 12,
+  "patch_size": 2,
+  "scale_factor_spatial": 16,
+  "scale_factor_temporal": 4,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 48
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cce4b09a5b92e850bcc70bd60bfb77a935ac79140bf53cbba289c2aebaa5e3f
+size 2818777776

vision_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "Qwen3VLVisionModel"
+  ],
+  "deepstack_visual_indexes": [
+    8,
+    16,
+    24
+  ],
+  "depth": 27,
+  "dtype": "float32",
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "in_channels": 3,
+  "initializer_range": 0.02,
+  "intermediate_size": 4304,
+  "model_type": "qwen3_vl",
+  "num_heads": 16,
+  "num_position_embeddings": 2304,
+  "out_hidden_size": 4096,
+  "patch_size": 16,
+  "spatial_merge_size": 2,
+  "temporal_patch_size": 2,
+  "transformers_version": "4.57.6"
+}

vision_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f60c80a91ad70452c16bcca22d4fa651508db9e18c0f5a08f2f25a2019b69f9
+size 2305588032