Upload 20 files

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

audio_vae/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "AutoencoderKLLTX2Audio",
+  "_diffusers_version": "0.38.0.dev0",
+  "attn_resolutions": null,
+  "base_channels": 128,
+  "causality_axis": "height",
+  "ch_mult": [
+    1,
+    2,
+    4
+  ],
+  "double_z": true,
+  "dropout": 0.0,
+  "in_channels": 2,
+  "is_causal": true,
+  "latent_channels": 8,
+  "mel_bins": 64,
+  "mel_hop_length": 160,
+  "mid_block_add_attention": false,
+  "norm_type": "pixel",
+  "num_res_blocks": 2,
+  "output_channels": 2,
+  "resolution": 256,
+  "sample_rate": 16000
+}

audio_vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dcb1c3cffc8c8b7710a04dd19500e481daff31f5ea8e8529f2cf697c439d12
+size 106507972

connectors/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "LTX2TextConnectors",
+  "_diffusers_version": "0.38.0.dev0",
+  "audio_connector_attention_head_dim": 64,
+  "audio_connector_num_attention_heads": 32,
+  "audio_connector_num_layers": 8,
+  "audio_connector_num_learnable_registers": 128,
+  "audio_gated_attn": true,
+  "audio_hidden_dim": 2048,
+  "caption_channels": 3840,
+  "causal_temporal_positioning": false,
+  "connector_rope_base_seq_len": 4096,
+  "per_modality_projections": true,
+  "proj_bias": true,
+  "rope_double_precision": true,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "text_proj_in_factor": 49,
+  "video_connector_attention_head_dim": 128,
+  "video_connector_num_attention_heads": 32,
+  "video_connector_num_layers": 8,
+  "video_connector_num_learnable_registers": 128,
+  "video_gated_attn": true,
+  "video_hidden_dim": 4096
+}

connectors/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bf5ca48db13cea180ecff2d8e8e1224fcea8cc04d41721e704c6034f914722
+size 6344489120

model_index.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "LTX2Pipeline",
+  "_diffusers_version": "0.38.0.dev0",
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Audio"
+  ],
+  "connectors": [
+    "ltx2",
+    "LTX2TextConnectors"
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Gemma3ForConditionalGeneration"
+  ],
+  "tokenizer": [
+    "transformers",
+    "GemmaTokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "LTX2VideoTransformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Video"
+  ],
+  "vocoder": [
+    "ltx2",
+    "LTX2VocoderWithBWE"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.32.0",
+  "base_image_seq_len": 1024,
+  "base_shift": 0.95,
+  "max_image_seq_len": 4096,
+  "max_shift": 2.05,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "use_dynamic_shifting": false,
+  "shift_terminal": null
+}

text_encoder/config.json

@@ -0,0 +1,683 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "quantization_config": {
+    "add_skip_keys": true,
+    "dequantize_fp32": false,
+    "dynamic_loss_threshold": 0.01,
+    "group_size": 0,
+    "is_integer": true,
+    "is_training": false,
+    "modules_dtype_dict": {
+      "int5": [
+        "model.language_model.layers.17.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight",
+        "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight"
+      ],
+      "uint4": [
+        "model.language_model.layers.0.mlp.down_proj.weight",
+        "model.language_model.layers.0.mlp.gate_proj.weight",
+        "model.language_model.layers.0.mlp.up_proj.weight",
+        "model.language_model.layers.0.self_attn.k_proj.weight",
+        "model.language_model.layers.0.self_attn.o_proj.weight",
+        "model.language_model.layers.0.self_attn.q_proj.weight",
+        "model.language_model.layers.0.self_attn.v_proj.weight",
+        "model.language_model.layers.1.mlp.down_proj.weight",
+        "model.language_model.layers.1.mlp.gate_proj.weight",
+        "model.language_model.layers.1.mlp.up_proj.weight",
+        "model.language_model.layers.1.self_attn.k_proj.weight",
+        "model.language_model.layers.1.self_attn.o_proj.weight",
+        "model.language_model.layers.1.self_attn.q_proj.weight",
+        "model.language_model.layers.1.self_attn.v_proj.weight",
+        "model.language_model.layers.2.mlp.down_proj.weight",
+        "model.language_model.layers.2.mlp.gate_proj.weight",
+        "model.language_model.layers.2.mlp.up_proj.weight",
+        "model.language_model.layers.2.self_attn.k_proj.weight",
+        "model.language_model.layers.2.self_attn.o_proj.weight",
+        "model.language_model.layers.2.self_attn.q_proj.weight",
+        "model.language_model.layers.2.self_attn.v_proj.weight",
+        "model.language_model.layers.3.mlp.down_proj.weight",
+        "model.language_model.layers.3.mlp.gate_proj.weight",
+        "model.language_model.layers.3.mlp.up_proj.weight",
+        "model.language_model.layers.3.self_attn.k_proj.weight",
+        "model.language_model.layers.3.self_attn.o_proj.weight",
+        "model.language_model.layers.3.self_attn.q_proj.weight",
+        "model.language_model.layers.3.self_attn.v_proj.weight",
+        "model.language_model.layers.4.mlp.down_proj.weight",
+        "model.language_model.layers.4.mlp.gate_proj.weight",
+        "model.language_model.layers.4.mlp.up_proj.weight",
+        "model.language_model.layers.4.self_attn.k_proj.weight",
+        "model.language_model.layers.4.self_attn.o_proj.weight",
+        "model.language_model.layers.4.self_attn.q_proj.weight",
+        "model.language_model.layers.4.self_attn.v_proj.weight",
+        "model.language_model.layers.5.mlp.down_proj.weight",
+        "model.language_model.layers.5.mlp.gate_proj.weight",
+        "model.language_model.layers.5.mlp.up_proj.weight",
+        "model.language_model.layers.5.self_attn.k_proj.weight",
+        "model.language_model.layers.5.self_attn.o_proj.weight",
+        "model.language_model.layers.5.self_attn.q_proj.weight",
+        "model.language_model.layers.5.self_attn.v_proj.weight",
+        "model.language_model.layers.6.mlp.down_proj.weight",
+        "model.language_model.layers.6.mlp.gate_proj.weight",
+        "model.language_model.layers.6.mlp.up_proj.weight",
+        "model.language_model.layers.6.self_attn.k_proj.weight",
+        "model.language_model.layers.6.self_attn.o_proj.weight",
+        "model.language_model.layers.6.self_attn.q_proj.weight",
+        "model.language_model.layers.6.self_attn.v_proj.weight",
+        "model.language_model.layers.7.mlp.down_proj.weight",
+        "model.language_model.layers.7.mlp.gate_proj.weight",
+        "model.language_model.layers.7.mlp.up_proj.weight",
+        "model.language_model.layers.7.self_attn.k_proj.weight",
+        "model.language_model.layers.7.self_attn.o_proj.weight",
+        "model.language_model.layers.7.self_attn.q_proj.weight",
+        "model.language_model.layers.7.self_attn.v_proj.weight",
+        "model.language_model.layers.8.mlp.down_proj.weight",
+        "model.language_model.layers.8.mlp.gate_proj.weight",
+        "model.language_model.layers.8.mlp.up_proj.weight",
+        "model.language_model.layers.8.self_attn.k_proj.weight",
+        "model.language_model.layers.8.self_attn.o_proj.weight",
+        "model.language_model.layers.8.self_attn.q_proj.weight",
+        "model.language_model.layers.8.self_attn.v_proj.weight",
+        "model.language_model.layers.9.mlp.down_proj.weight",
+        "model.language_model.layers.9.mlp.gate_proj.weight",
+        "model.language_model.layers.9.mlp.up_proj.weight",
+        "model.language_model.layers.9.self_attn.k_proj.weight",
+        "model.language_model.layers.9.self_attn.o_proj.weight",
+        "model.language_model.layers.9.self_attn.q_proj.weight",
+        "model.language_model.layers.9.self_attn.v_proj.weight",
+        "model.language_model.layers.10.mlp.down_proj.weight",
+        "model.language_model.layers.10.mlp.gate_proj.weight",
+        "model.language_model.layers.10.mlp.up_proj.weight",
+        "model.language_model.layers.10.self_attn.k_proj.weight",
+        "model.language_model.layers.10.self_attn.o_proj.weight",
+        "model.language_model.layers.10.self_attn.q_proj.weight",
+        "model.language_model.layers.10.self_attn.v_proj.weight",
+        "model.language_model.layers.11.mlp.down_proj.weight",
+        "model.language_model.layers.11.mlp.gate_proj.weight",
+        "model.language_model.layers.11.mlp.up_proj.weight",
+        "model.language_model.layers.11.self_attn.k_proj.weight",
+        "model.language_model.layers.11.self_attn.o_proj.weight",
+        "model.language_model.layers.11.self_attn.q_proj.weight",
+        "model.language_model.layers.11.self_attn.v_proj.weight",
+        "model.language_model.layers.12.mlp.down_proj.weight",
+        "model.language_model.layers.12.mlp.gate_proj.weight",
+        "model.language_model.layers.12.mlp.up_proj.weight",
+        "model.language_model.layers.12.self_attn.k_proj.weight",
+        "model.language_model.layers.12.self_attn.o_proj.weight",
+        "model.language_model.layers.12.self_attn.q_proj.weight",
+        "model.language_model.layers.12.self_attn.v_proj.weight",
+        "model.language_model.layers.13.mlp.down_proj.weight",
+        "model.language_model.layers.13.mlp.gate_proj.weight",
+        "model.language_model.layers.13.mlp.up_proj.weight",
+        "model.language_model.layers.13.self_attn.k_proj.weight",
+        "model.language_model.layers.13.self_attn.o_proj.weight",
+        "model.language_model.layers.13.self_attn.q_proj.weight",
+        "model.language_model.layers.13.self_attn.v_proj.weight",
+        "model.language_model.layers.14.mlp.down_proj.weight",
+        "model.language_model.layers.14.mlp.gate_proj.weight",
+        "model.language_model.layers.14.mlp.up_proj.weight",
+        "model.language_model.layers.14.self_attn.k_proj.weight",
+        "model.language_model.layers.14.self_attn.o_proj.weight",
+        "model.language_model.layers.14.self_attn.q_proj.weight",
+        "model.language_model.layers.14.self_attn.v_proj.weight",
+        "model.language_model.layers.15.mlp.down_proj.weight",
+        "model.language_model.layers.15.mlp.gate_proj.weight",
+        "model.language_model.layers.15.mlp.up_proj.weight",
+        "model.language_model.layers.15.self_attn.k_proj.weight",
+        "model.language_model.layers.15.self_attn.o_proj.weight",
+        "model.language_model.layers.15.self_attn.q_proj.weight",
+        "model.language_model.layers.15.self_attn.v_proj.weight",
+        "model.language_model.layers.16.mlp.down_proj.weight",
+        "model.language_model.layers.16.mlp.gate_proj.weight",
+        "model.language_model.layers.16.mlp.up_proj.weight",
+        "model.language_model.layers.16.self_attn.k_proj.weight",
+        "model.language_model.layers.16.self_attn.o_proj.weight",
+        "model.language_model.layers.16.self_attn.q_proj.weight",
+        "model.language_model.layers.16.self_attn.v_proj.weight",
+        "model.language_model.layers.17.mlp.down_proj.weight",
+        "model.language_model.layers.17.mlp.gate_proj.weight",
+        "model.language_model.layers.17.mlp.up_proj.weight",
+        "model.language_model.layers.17.self_attn.o_proj.weight",
+        "model.language_model.layers.17.self_attn.q_proj.weight",
+        "model.language_model.layers.17.self_attn.v_proj.weight",
+        "model.language_model.layers.18.mlp.down_proj.weight",
+        "model.language_model.layers.18.mlp.gate_proj.weight",
+        "model.language_model.layers.18.mlp.up_proj.weight",
+        "model.language_model.layers.18.self_attn.k_proj.weight",
+        "model.language_model.layers.18.self_attn.o_proj.weight",
+        "model.language_model.layers.18.self_attn.q_proj.weight",
+        "model.language_model.layers.18.self_attn.v_proj.weight",
+        "model.language_model.layers.19.mlp.down_proj.weight",
+        "model.language_model.layers.19.mlp.gate_proj.weight",
+        "model.language_model.layers.19.mlp.up_proj.weight",
+        "model.language_model.layers.19.self_attn.k_proj.weight",
+        "model.language_model.layers.19.self_attn.o_proj.weight",
+        "model.language_model.layers.19.self_attn.q_proj.weight",
+        "model.language_model.layers.19.self_attn.v_proj.weight",
+        "model.language_model.layers.20.mlp.down_proj.weight",
+        "model.language_model.layers.20.mlp.gate_proj.weight",
+        "model.language_model.layers.20.mlp.up_proj.weight",
+        "model.language_model.layers.20.self_attn.k_proj.weight",
+        "model.language_model.layers.20.self_attn.o_proj.weight",
+        "model.language_model.layers.20.self_attn.q_proj.weight",
+        "model.language_model.layers.20.self_attn.v_proj.weight",
+        "model.language_model.layers.21.mlp.down_proj.weight",
+        "model.language_model.layers.21.mlp.gate_proj.weight",
+        "model.language_model.layers.21.mlp.up_proj.weight",
+        "model.language_model.layers.21.self_attn.k_proj.weight",
+        "model.language_model.layers.21.self_attn.o_proj.weight",
+        "model.language_model.layers.21.self_attn.q_proj.weight",
+        "model.language_model.layers.21.self_attn.v_proj.weight",
+        "model.language_model.layers.22.mlp.down_proj.weight",
+        "model.language_model.layers.22.mlp.gate_proj.weight",
+        "model.language_model.layers.22.mlp.up_proj.weight",
+        "model.language_model.layers.22.self_attn.k_proj.weight",
+        "model.language_model.layers.22.self_attn.o_proj.weight",
+        "model.language_model.layers.22.self_attn.q_proj.weight",
+        "model.language_model.layers.22.self_attn.v_proj.weight",
+        "model.language_model.layers.23.mlp.down_proj.weight",
+        "model.language_model.layers.23.mlp.gate_proj.weight",
+        "model.language_model.layers.23.mlp.up_proj.weight",
+        "model.language_model.layers.23.self_attn.k_proj.weight",
+        "model.language_model.layers.23.self_attn.o_proj.weight",
+        "model.language_model.layers.23.self_attn.q_proj.weight",
+        "model.language_model.layers.23.self_attn.v_proj.weight",
+        "model.language_model.layers.24.mlp.down_proj.weight",
+        "model.language_model.layers.24.mlp.gate_proj.weight",
+        "model.language_model.layers.24.mlp.up_proj.weight",
+        "model.language_model.layers.24.self_attn.k_proj.weight",
+        "model.language_model.layers.24.self_attn.o_proj.weight",
+        "model.language_model.layers.24.self_attn.q_proj.weight",
+        "model.language_model.layers.24.self_attn.v_proj.weight",
+        "model.language_model.layers.25.mlp.down_proj.weight",
+        "model.language_model.layers.25.mlp.gate_proj.weight",
+        "model.language_model.layers.25.mlp.up_proj.weight",
+        "model.language_model.layers.25.self_attn.k_proj.weight",
+        "model.language_model.layers.25.self_attn.o_proj.weight",
+        "model.language_model.layers.25.self_attn.q_proj.weight",
+        "model.language_model.layers.25.self_attn.v_proj.weight",
+        "model.language_model.layers.26.mlp.down_proj.weight",
+        "model.language_model.layers.26.mlp.gate_proj.weight",
+        "model.language_model.layers.26.mlp.up_proj.weight",
+        "model.language_model.layers.26.self_attn.k_proj.weight",
+        "model.language_model.layers.26.self_attn.o_proj.weight",
+        "model.language_model.layers.26.self_attn.q_proj.weight",
+        "model.language_model.layers.26.self_attn.v_proj.weight",
+        "model.language_model.layers.27.mlp.down_proj.weight",
+        "model.language_model.layers.27.mlp.gate_proj.weight",
+        "model.language_model.layers.27.mlp.up_proj.weight",
+        "model.language_model.layers.27.self_attn.k_proj.weight",
+        "model.language_model.layers.27.self_attn.o_proj.weight",
+        "model.language_model.layers.27.self_attn.q_proj.weight",
+        "model.language_model.layers.27.self_attn.v_proj.weight",
+        "model.language_model.layers.28.mlp.down_proj.weight",
+        "model.language_model.layers.28.mlp.gate_proj.weight",
+        "model.language_model.layers.28.mlp.up_proj.weight",
+        "model.language_model.layers.28.self_attn.k_proj.weight",
+        "model.language_model.layers.28.self_attn.o_proj.weight",
+        "model.language_model.layers.28.self_attn.q_proj.weight",
+        "model.language_model.layers.28.self_attn.v_proj.weight",
+        "model.language_model.layers.29.mlp.down_proj.weight",
+        "model.language_model.layers.29.mlp.gate_proj.weight",
+        "model.language_model.layers.29.mlp.up_proj.weight",
+        "model.language_model.layers.29.self_attn.k_proj.weight",
+        "model.language_model.layers.29.self_attn.o_proj.weight",
+        "model.language_model.layers.29.self_attn.q_proj.weight",
+        "model.language_model.layers.29.self_attn.v_proj.weight",
+        "model.language_model.layers.30.mlp.down_proj.weight",
+        "model.language_model.layers.30.mlp.gate_proj.weight",
+        "model.language_model.layers.30.mlp.up_proj.weight",
+        "model.language_model.layers.30.self_attn.k_proj.weight",
+        "model.language_model.layers.30.self_attn.o_proj.weight",
+        "model.language_model.layers.30.self_attn.q_proj.weight",
+        "model.language_model.layers.30.self_attn.v_proj.weight",
+        "model.language_model.layers.31.mlp.down_proj.weight",
+        "model.language_model.layers.31.mlp.gate_proj.weight",
+        "model.language_model.layers.31.mlp.up_proj.weight",
+        "model.language_model.layers.31.self_attn.k_proj.weight",
+        "model.language_model.layers.31.self_attn.o_proj.weight",
+        "model.language_model.layers.31.self_attn.q_proj.weight",
+        "model.language_model.layers.31.self_attn.v_proj.weight",
+        "model.language_model.layers.32.mlp.down_proj.weight",
+        "model.language_model.layers.32.mlp.gate_proj.weight",
+        "model.language_model.layers.32.mlp.up_proj.weight",
+        "model.language_model.layers.32.self_attn.k_proj.weight",
+        "model.language_model.layers.32.self_attn.o_proj.weight",
+        "model.language_model.layers.32.self_attn.q_proj.weight",
+        "model.language_model.layers.32.self_attn.v_proj.weight",
+        "model.language_model.layers.33.mlp.down_proj.weight",
+        "model.language_model.layers.33.mlp.gate_proj.weight",
+        "model.language_model.layers.33.mlp.up_proj.weight",
+        "model.language_model.layers.33.self_attn.k_proj.weight",
+        "model.language_model.layers.33.self_attn.o_proj.weight",
+        "model.language_model.layers.33.self_attn.q_proj.weight",
+        "model.language_model.layers.33.self_attn.v_proj.weight",
+        "model.language_model.layers.34.mlp.down_proj.weight",
+        "model.language_model.layers.34.mlp.gate_proj.weight",
+        "model.language_model.layers.34.mlp.up_proj.weight",
+        "model.language_model.layers.34.self_attn.k_proj.weight",
+        "model.language_model.layers.34.self_attn.o_proj.weight",
+        "model.language_model.layers.34.self_attn.q_proj.weight",
+        "model.language_model.layers.34.self_attn.v_proj.weight",
+        "model.language_model.layers.35.mlp.down_proj.weight",
+        "model.language_model.layers.35.mlp.gate_proj.weight",
+        "model.language_model.layers.35.mlp.up_proj.weight",
+        "model.language_model.layers.35.self_attn.k_proj.weight",
+        "model.language_model.layers.35.self_attn.o_proj.weight",
+        "model.language_model.layers.35.self_attn.q_proj.weight",
+        "model.language_model.layers.35.self_attn.v_proj.weight",
+        "model.language_model.layers.36.mlp.down_proj.weight",
+        "model.language_model.layers.36.mlp.gate_proj.weight",
+        "model.language_model.layers.36.mlp.up_proj.weight",
+        "model.language_model.layers.36.self_attn.k_proj.weight",
+        "model.language_model.layers.36.self_attn.o_proj.weight",
+        "model.language_model.layers.36.self_attn.q_proj.weight",
+        "model.language_model.layers.36.self_attn.v_proj.weight",
+        "model.language_model.layers.37.mlp.down_proj.weight",
+        "model.language_model.layers.37.mlp.gate_proj.weight",
+        "model.language_model.layers.37.mlp.up_proj.weight",
+        "model.language_model.layers.37.self_attn.k_proj.weight",
+        "model.language_model.layers.37.self_attn.o_proj.weight",
+        "model.language_model.layers.37.self_attn.q_proj.weight",
+        "model.language_model.layers.37.self_attn.v_proj.weight",
+        "model.language_model.layers.38.mlp.down_proj.weight",
+        "model.language_model.layers.38.mlp.gate_proj.weight",
+        "model.language_model.layers.38.mlp.up_proj.weight",
+        "model.language_model.layers.38.self_attn.k_proj.weight",
+        "model.language_model.layers.38.self_attn.o_proj.weight",
+        "model.language_model.layers.38.self_attn.q_proj.weight",
+        "model.language_model.layers.38.self_attn.v_proj.weight",
+        "model.language_model.layers.39.mlp.down_proj.weight",
+        "model.language_model.layers.39.mlp.gate_proj.weight",
+        "model.language_model.layers.39.mlp.up_proj.weight",
+        "model.language_model.layers.39.self_attn.k_proj.weight",
+        "model.language_model.layers.39.self_attn.o_proj.weight",
+        "model.language_model.layers.39.self_attn.q_proj.weight",
+        "model.language_model.layers.39.self_attn.v_proj.weight",
+        "model.language_model.layers.40.mlp.down_proj.weight",
+        "model.language_model.layers.40.mlp.gate_proj.weight",
+        "model.language_model.layers.40.mlp.up_proj.weight",
+        "model.language_model.layers.40.self_attn.k_proj.weight",
+        "model.language_model.layers.40.self_attn.o_proj.weight",
+        "model.language_model.layers.40.self_attn.q_proj.weight",
+        "model.language_model.layers.40.self_attn.v_proj.weight",
+        "model.language_model.layers.41.mlp.down_proj.weight",
+        "model.language_model.layers.41.mlp.gate_proj.weight",
+        "model.language_model.layers.41.mlp.up_proj.weight",
+        "model.language_model.layers.41.self_attn.k_proj.weight",
+        "model.language_model.layers.41.self_attn.o_proj.weight",
+        "model.language_model.layers.41.self_attn.q_proj.weight",
+        "model.language_model.layers.41.self_attn.v_proj.weight",
+        "model.language_model.layers.42.mlp.down_proj.weight",
+        "model.language_model.layers.42.mlp.gate_proj.weight",
+        "model.language_model.layers.42.mlp.up_proj.weight",
+        "model.language_model.layers.42.self_attn.k_proj.weight",
+        "model.language_model.layers.42.self_attn.o_proj.weight",
+        "model.language_model.layers.42.self_attn.q_proj.weight",
+        "model.language_model.layers.42.self_attn.v_proj.weight",
+        "model.language_model.layers.43.mlp.down_proj.weight",
+        "model.language_model.layers.43.mlp.gate_proj.weight",
+        "model.language_model.layers.43.mlp.up_proj.weight",
+        "model.language_model.layers.43.self_attn.k_proj.weight",
+        "model.language_model.layers.43.self_attn.o_proj.weight",
+        "model.language_model.layers.43.self_attn.q_proj.weight",
+        "model.language_model.layers.43.self_attn.v_proj.weight",
+        "model.language_model.layers.44.mlp.down_proj.weight",
+        "model.language_model.layers.44.mlp.gate_proj.weight",
+        "model.language_model.layers.44.mlp.up_proj.weight",
+        "model.language_model.layers.44.self_attn.k_proj.weight",
+        "model.language_model.layers.44.self_attn.o_proj.weight",
+        "model.language_model.layers.44.self_attn.q_proj.weight",
+        "model.language_model.layers.44.self_attn.v_proj.weight",
+        "model.language_model.layers.45.mlp.down_proj.weight",
+        "model.language_model.layers.45.mlp.gate_proj.weight",
+        "model.language_model.layers.45.mlp.up_proj.weight",
+        "model.language_model.layers.45.self_attn.k_proj.weight",
+        "model.language_model.layers.45.self_attn.o_proj.weight",
+        "model.language_model.layers.45.self_attn.q_proj.weight",
+        "model.language_model.layers.45.self_attn.v_proj.weight",
+        "model.language_model.layers.46.mlp.down_proj.weight",
+        "model.language_model.layers.46.mlp.gate_proj.weight",
+        "model.language_model.layers.46.mlp.up_proj.weight",
+        "model.language_model.layers.46.self_attn.k_proj.weight",
+        "model.language_model.layers.46.self_attn.o_proj.weight",
+        "model.language_model.layers.46.self_attn.q_proj.weight",
+        "model.language_model.layers.46.self_attn.v_proj.weight",
+        "model.language_model.layers.47.mlp.down_proj.weight",
+        "model.language_model.layers.47.mlp.gate_proj.weight",
+        "model.language_model.layers.47.mlp.up_proj.weight",
+        "model.language_model.layers.47.self_attn.k_proj.weight",
+        "model.language_model.layers.47.self_attn.o_proj.weight",
+        "model.language_model.layers.47.self_attn.q_proj.weight",
+        "model.language_model.layers.47.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight",
+        "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight",
+        "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight"
+      ]
+    },
+    "modules_quant_config": {},
+    "modules_to_not_convert": [
+      ".context_embedder",
+      ".x_embedder",
+      ".txt_in",
+      ".emb_in",
+      ".t_embedder",
+      ".time_embed",
+      "patch_embed",
+      "model.language_model.embed_tokens.weight",
+      "multi_modal_projector",
+      "patch_embedding",
+      ".norm_out",
+      ".vid_out",
+      ".img_in",
+      "patch_emb",
+      ".img_out",
+      "wte",
+      ".final_layer",
+      ".txt_out",
+      "time_text_embed",
+      ".vid_in",
+      ".emb_out",
+      ".condition_embedder",
+      ".proj_out",
+      "lm_head",
+      ".y_embedder",
+      "model.language_model.embed_tokens",
+      "lm_head.weight"
+    ],
+    "non_blocking": false,
+    "quant_conv": false,
+    "quant_method": "sdnq",
+    "quantization_device": null,
+    "quantized_matmul_dtype": null,
+    "return_device": null,
+    "sdnq_version": "0.1.6",
+    "svd_rank": 32,
+    "svd_steps": 8,
+    "use_dynamic_quantization": true,
+    "use_grad_ckpt": true,
+    "use_quantized_matmul": false,
+    "use_quantized_matmul_conv": false,
+    "use_static_quantization": true,
+    "use_stochastic_rounding": false,
+    "use_svd": false,
+    "weights_dtype": "uint4"
+  },
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "dtype": "bfloat16",
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "factor": 8.0,
+        "rope_theta": 1000000,
+        "rope_type": "linear"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "tie_word_embeddings": true,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

text_encoder/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.3.0"
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac9cddb289172beaa35cc252d45fa57a59dda762e74cd0bf495cb6349e2282b
+size 8331205104

tokenizer/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443

tokenizer/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ccc76f3d3d6919ad6b9403d2398ffe2f58b9af820ce34393a7ae705b05bb9d
+size 10000432888

transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d112b824ac400de39cf06cd5347dd428ce9573a63ea932cf6d00731b4c3b1ae7
+size 1536061816

vae/config.json

@@ -0,0 +1,93 @@
+{
+  "_class_name": "AutoencoderKLLTX2Video",
+  "_diffusers_version": "0.38.0.dev0",
+  "block_out_channels": [
+    256,
+    512,
+    1024,
+    1024
+  ],
+  "decoder_block_out_channels": [
+    256,
+    512,
+    512,
+    1024
+  ],
+  "decoder_causal": false,
+  "decoder_inject_noise": [
+    false,
+    false,
+    false,
+    false,
+    false
+  ],
+  "decoder_layers_per_block": [
+    4,
+    6,
+    4,
+    2,
+    2
+  ],
+  "decoder_spatial_padding_mode": "zeros",
+  "decoder_spatio_temporal_scaling": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "down_block_types": [
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D"
+  ],
+  "downsample_type": [
+    "spatial",
+    "temporal",
+    "spatiotemporal",
+    "spatiotemporal"
+  ],
+  "encoder_causal": true,
+  "encoder_spatial_padding_mode": "zeros",
+  "in_channels": 3,
+  "latent_channels": 128,
+  "layers_per_block": [
+    4,
+    6,
+    4,
+    2,
+    2
+  ],
+  "out_channels": 3,
+  "patch_size": 4,
+  "patch_size_t": 1,
+  "resnet_norm_eps": 1e-06,
+  "scaling_factor": 1.0,
+  "spatial_compression_ratio": 32,
+  "spatio_temporal_scaling": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "temporal_compression_ratio": 8,
+  "timestep_conditioning": false,
+  "upsample_factor": [
+    2,
+    2,
+    1,
+    2
+  ],
+  "upsample_residual": [
+    false,
+    false,
+    false,
+    false
+  ],
+  "upsample_type": [
+    "spatiotemporal",
+    "spatiotemporal",
+    "temporal",
+    "spatial"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425f0dfa227dee5d0ff3d9720563370810409a439c302ca74f0f944057ce55c5
+size 1452233194

vocoder/config.json

@@ -0,0 +1,104 @@
+{
+  "_class_name": "LTX2VocoderWithBWE",
+  "_diffusers_version": "0.38.0.dev0",
+  "act_fn": "snakebeta",
+  "antialias": true,
+  "antialias_kernel_size": 12,
+  "antialias_ratio": 2,
+  "bwe_act_fn": "snakebeta",
+  "bwe_antialias": true,
+  "bwe_antialias_kernel_size": 12,
+  "bwe_antialias_ratio": 2,
+  "bwe_final_act_fn": null,
+  "bwe_final_bias": false,
+  "bwe_hidden_channels": 512,
+  "bwe_in_channels": 128,
+  "bwe_leaky_relu_negative_slope": 0.1,
+  "bwe_out_channels": 2,
+  "bwe_resnet_dilations": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "bwe_resnet_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "bwe_upsample_factors": [
+    6,
+    5,
+    2,
+    2,
+    2
+  ],
+  "bwe_upsample_kernel_sizes": [
+    12,
+    11,
+    4,
+    4,
+    4
+  ],
+  "filter_length": 512,
+  "final_act_fn": null,
+  "final_bias": false,
+  "hidden_channels": 1536,
+  "hop_length": 80,
+  "in_channels": 128,
+  "input_sampling_rate": 16000,
+  "leaky_relu_negative_slope": 0.1,
+  "num_mel_channels": 64,
+  "out_channels": 2,
+  "output_sampling_rate": 48000,
+  "resnet_dilations": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resnet_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "upsample_factors": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "upsample_kernel_sizes": [
+    11,
+    4,
+    4,
+    4,
+    4,
+    4
+  ],
+  "window_length": 512
+}

vocoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99dde145a982974bc4c39608b3b929f232f0126a55d8326a47ad54f486ae23c
+size 258305056