lianglv commited on 13 days ago

Commit

d2fe5fe

verified ·

1 Parent(s): f055f54

Upload folder using huggingface_hub

Browse files

Files changed (34) hide show

.gitattributes +1 -0
chat_template.json +3 -0
config.json +259 -0
generation_config.json +14 -0
merges.txt +0 -0
model_index.json +29 -0
preprocessor_config.json +21 -0
scheduler/scheduler_config.json +33 -0
sound_tokenizer/config.json +64 -0
sound_tokenizer/diffusion_pytorch_model.safetensors +3 -0
text_tokenizer/added_tokens.json +28 -0
text_tokenizer/chat_template.jinja +120 -0
text_tokenizer/merges.txt +0 -0
text_tokenizer/special_tokens_map.json +31 -0
text_tokenizer/tokenizer.json +3 -0
text_tokenizer/tokenizer_config.json +239 -0
text_tokenizer/vocab.json +0 -0
tokenizer.json +0 -0
tokenizer_config.json +239 -0
transformer/config.json +132 -0
transformer/model-00001-of-00004.safetensors +3 -0
transformer/model-00002-of-00004.safetensors +3 -0
transformer/model-00003-of-00004.safetensors +3 -0
transformer/model-00004-of-00004.safetensors +3 -0
transformer/model.safetensors.index.json +0 -0
transformer/model_extra_tensors.safetensors +3 -0
transformer/preprocessor_config.json +21 -0
transformer/quantization_config.json +17 -0
vae/config.json +129 -0
vae/diffusion_pytorch_model.safetensors +3 -0
video_preprocessor_config.json +21 -0
vision_encoder/config.json +25 -0
vision_encoder/model.safetensors +3 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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

chat_template.json ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

config.json ADDED Viewed

	@@ -0,0 +1,259 @@

+{
+  "allow_patterns_overrides": [
+    "*/*.safetensors"
+  ],
+  "architectures": [
+    "Cosmos3ForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model": {
+    "_recursive_": false,
+    "_target": "omni_mot_model",
+    "config": {
+      "_type": "omni_mot_model_config",
+      "action_gen": true,
+      "activation_checkpointing": {
+        "_type": "activation_checkpointing_config",
+        "determinism_check": "default",
+        "mode": "selective",
+        "preserve_rng_state": true,
+        "save_ops_regex": [
+          "fmha"
+        ]
+      },
+      "causal_training_strategy": "none",
+      "diffusion_expert_config": {
+        "_type": "diffusion_expert_config",
+        "base_fps": 24,
+        "enable_fps_modulation": true,
+        "load_weights_from_pretrained": false,
+        "max_vae_latent_side_after_patchify": 20,
+        "patch_spatial": 2,
+        "position_embedding_type": "unified_3d_mrope",
+        "rope_h_extrapolation_ratio": 1.0,
+        "rope_t_extrapolation_ratio": 1.0,
+        "rope_w_extrapolation_ratio": 1.0,
+        "timestep_range": 1.0,
+        "unified_3d_mrope_reset_spatial_ids": true,
+        "unified_3d_mrope_temporal_modality_margin": 15000
+      },
+      "ema": {
+        "_type": "ema_config",
+        "enabled": false,
+        "iteration_shift": 0,
+        "rate": 0.1
+      },
+      "fixed_step_sampler_config": null,
+      "input_caption_key": "ai_caption",
+      "input_image_key": "images",
+      "input_video_key": "video",
+      "joint_attn_implementation": "two_way",
+      "latent_downsample_factor": 16,
+      "lbl": {
+        "_type": "lbl_config",
+        "coeff_gen": null,
+        "coeff_und": null,
+        "method": "local"
+      },
+      "log_enc_time_every_n": 100,
+      "lora_alpha": 32,
+      "lora_enabled": false,
+      "lora_rank": 16,
+      "lora_target_modules": "q_proj_moe_gen,k_proj_moe_gen,v_proj_moe_gen,o_proj_moe_gen",
+      "max_action_dim": 64,
+      "max_num_tokens_after_packing": 74000,
+      "natten_parameter_list": null,
+      "net": null,
+      "num_embodiment_domains": 32,
+      "parallelism": {
+        "_type": "parallelism_config",
+        "cfg_parallel_shard_degree": 1,
+        "compile_dynamic": true,
+        "compiled_region": "language",
+        "context_parallel_shard_degree": 1,
+        "coordinate_descent_tuning": false,
+        "data_parallel_replicate_degree": 1,
+        "data_parallel_shard_degree": 8,
+        "enable_inference_mode": false,
+        "max_autotune_pointwise": false,
+        "precision": "bfloat16",
+        "use_cuda_graphs": false,
+        "use_torch_compile": true
+      },
+      "rectified_flow_inference_config": {
+        "_type": "rectified_flow_inference_config",
+        "num_train_timesteps": 1000,
+        "scheduler_type": "unipc",
+        "shift": 1,
+        "use_dynamic_shifting": false
+      },
+      "rectified_flow_training_config": {
+        "_type": "rectified_flow_training_config",
+        "action_loss_weight": 10.0,
+        "high_sigma_ratio": 0.05,
+        "high_sigma_timesteps_max": 1000,
+        "high_sigma_timesteps_min": 995,
+        "image_loss_scale": null,
+        "independent_action_schedule": false,
+        "independent_sound_schedule": false,
+        "loss_scale": 10.0,
+        "normalize_loss_by_active": false,
+        "shift": {
+          "256": 3,
+          "480": 5,
+          "720": 10
+        },
+        "shift_action": null,
+        "shift_sound": null,
+        "sound_loss_scale": 2.0,
+        "train_time_action_distribution": "logitnormal",
+        "train_time_image_distribution": "logitnormal",
+        "train_time_sound_distribution": "logitnormal",
+        "train_time_video_distribution": "waver",
+        "train_time_weight": "uniform",
+        "use_discrete_rf": false,
+        "use_dynamic_shift": false,
+        "use_high_sigma_strategy": false,
+        "use_high_sigma_strategy_action": false,
+        "use_high_sigma_strategy_sound": false
+      },
+      "resolution": "720",
+      "sound_dim": 64,
+      "sound_gen": true,
+      "sound_latent_fps": 25,
+      "sound_tokenizer": {
+        "_target": "avae_interface",
+        "audio_channels": 2,
+        "avae_config_path": "",
+        "avae_path": "pretrained/tokenizers/audio/avae/avae_48k_noncausal_25hz_64ch.ckpt",
+        "bucket_name": "bucket",
+        "hop_size": 1920,
+        "io_channels": 64,
+        "latent_mean": null,
+        "latent_std": null,
+        "normalization_type": "none",
+        "normalize_latents": false,
+        "object_store_credential_path_pretrained": "credentials/gcp_training.secret",
+        "sample_rate": 48000,
+        "tanh_clamp": 0.995,
+        "tanh_input_scale": 1.5,
+        "tanh_output_scale": 3.5
+      },
+      "state_ch": 48,
+      "state_t": 300,
+      "tokenizer": {
+        "_target": "wan2pt2_vae_interface",
+        "bucket_name": "bucket",
+        "chunk_duration": 93,
+        "encode_bucket_multiple": null,
+        "encode_chunk_frames": {
+          "256": 68,
+          "480": 24,
+          "720": 12
+        },
+        "encode_exact_durations": [
+          17,
+          61,
+          73
+        ],
+        "keep_decoder_cache": false,
+        "object_store_credential_path_pretrained": "credentials/gcp_training.secret",
+        "spatial_compression_factor": 16,
+        "temporal_compression_factor": 4,
+        "temporal_window": null,
+        "use_streaming_encode": false,
+        "vae_path": "pretrained/tokenizers/video/wan2pt2/Wan2.2_VAE.pth"
+      },
+      "video_temporal_causal": false,
+      "vision_gen": true,
+      "vlm_config": {
+        "_type": "vlm_config",
+        "layer_module": null,
+        "model_instance": {
+          "_target": "qwen3_vl_text_for_causal_lm",
+          "config": {
+            "_target": "create_vlm_config",
+            "base_config": {
+              "_target": "qwen3_vl_mot_config_from_json_file",
+              "json_file": "cosmos3://vfm/models/vlm/qwen3_vl/configs/Qwen3-VL-8B-Instruct.json"
+            },
+            "qk_norm_for_text": true
+          }
+        },
+        "model_name": "nvidia/Cosmos3-Nano-Reasoner",
+        "pretrained_weights": {
+          "_type": "pretrained_weights_config",
+          "backbone_path": "s3://bucket/cosmos3/pretrained/huggingface/Cosmos-Reason/Cosmos3-Nano-Reasoner-bb9c6f5/",
+          "checkpoint_format": null,
+          "credentials_path": "credentials/gcp_checkpoint.secret",
+          "enable_gcs_patch_in_boto3": true,
+          "enabled": false
+        },
+        "qk_norm": false,
+        "tie_word_embeddings": false,
+        "tokenizer": {
+          "_target": "create_qwen2_tokenizer_with_download",
+          "config_variant": "gcp",
+          "pretrained_model_name": "Qwen/Qwen3-VL-8B-Instruct"
+        },
+        "use_system_prompt": false
+      }
+    }
+  },
+  "model_type": "cosmos3_omni",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "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
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.8,
+    "repetition_penalty": 1.0,
+    "temperature": 0.7,
+    "transformers_version": "4.56.0"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model_index.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_class_name": "Cosmos3OmniDiffusersPipeline",
+  "_diffusers_version": "0.37.1",
+  "_name_or_path": "/mnt/disk0/lvl/Cosmos3-Nano",
+  "scheduler": [
+    "diffusers",
+    "UniPCMultistepScheduler"
+  ],
+  "sound_tokenizer": [
+    "diffusers",
+    "Cosmos3AVAEAudioTokenizer"
+  ],
+  "text_tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "Cosmos3OmniTransformer"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan"
+  ],
+  "vision_encoder": [
+    "transformers",
+    "Qwen3VLVisionModel"
+  ]
+}

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

scheduler/scheduler_config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b6da5975bf89f6853fe589ad4752d281ac79fbdfad52ea90537fa080b4b9c2
+size 1985176840

text_tokenizer/added_tokens.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -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/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

text_tokenizer/special_tokens_map.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

text_tokenizer/tokenizer_config.json ADDED Viewed

	@@ -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
+}

text_tokenizer/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json ADDED Viewed

	@@ -0,0 +1,132 @@

+{
+  "_class_name": "Cosmos3VFMTransformer",
+  "_diffusers_version": "0.37.1",
+  "action_dim": 64,
+  "action_gen": true,
+  "architectures": [
+    "Cosmos3VFMTransformer"
+  ],
+  "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": "cosmos3_vllm_omni",
+  "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,
+  "quantization_config": {
+    "autoround_version": "0.14.0",
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": [
+      "language_model.layers",
+      "gen_layers",
+      "blocks",
+      "deepstack_merger_list"
+    ],
+    "data_type": "int",
+    "extra_config": {
+      "action_proj_in.bias": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "action_proj_in.fc": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "action_proj_out.bias": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "action_proj_out.fc": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "audio_proj_in": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "audio_proj_out": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "embed_tokens": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "merger.linear_fc1": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "merger.linear_fc2": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "pos_embed": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "proj_in": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "proj_out": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "time_embedder.linear_1": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "time_embedder.linear_2": {
+        "bits": 16,
+        "data_type": "fp"
+      }
+    },
+    "group_size": 128,
+    "nsamples": 16,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      24,
+      20,
+      20
+    ],
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "sound_dim": 64,
+  "sound_gen": true,
+  "sound_latent_fps": 25,
+  "temporal_compression_factor_sound": 1,
+  "timestep_scale": 0.001,
+  "transformers_version": "5.13.0",
+  "unified_3d_mrope_reset_spatial_ids": true,
+  "unified_3d_mrope_temporal_modality_margin": 15000,
+  "use_moe": true,
+  "video_temporal_causal": false,
+  "vocab_size": 151936
+}

transformer/model-00001-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d56a43de52dd0220720369f9967116db87499bb63ac09ecbca40da369a38f188
+size 2127171832

transformer/model-00002-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2991f7a45da7b025dc9c1d0fc164dc96272c4b85a622f41222597ab47deecf4
+size 2127205656

transformer/model-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:933bf8157833b37d67a028668132e0fe3cbba46e74d047ccb1654fcbbdbe0b64
+size 2135885216

transformer/model-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6299a2f503a55df73224d319f8f359ef942d8f35abf1788d41379f1dfe2dd9
+size 828237824

transformer/model.safetensors.index.json ADDED Viewed

The diff for this file is too large to render. See raw diff

transformer/model_extra_tensors.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa01a79817c81c197ba49e5c7b644c4def79fb1e2bb480cb73492c89c22eb22
+size 1685291408

transformer/preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

transformer/quantization_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "autoround_version": "0.14.0",
+  "batch_size": 1,
+  "bits": 4,
+  "block_name_to_quantize": [
+    "language_model.layers",
+    "gen_layers",
+    "blocks",
+    "deepstack_merger_list"
+  ],
+  "data_type": "int",
+  "group_size": 128,
+  "nsamples": 16,
+  "packing_format": "auto_round:auto_gptq",
+  "quant_method": "auto-round",
+  "sym": true
+}

vae/config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:230496cb59ff85bc9c040487737c4062480cb61c71e697b197b4c30142f2a0da
+size 1409400600

video_preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

vision_encoder/config.json ADDED Viewed

	@@ -0,0 +1,25 @@

+{
+  "architectures": [
+    "Qwen3VLVisionModel"
+  ],
+  "deepstack_visual_indexes": [
+    8,
+    16,
+    24
+  ],
+  "depth": 27,
+  "dtype": "bfloat16",
+  "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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c0f719fcf5f2cdadb676701477c236020713657976592ad046583707a6a95a
+size 1152811416

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff