Upload text_encoder folder with SDNQ weights

text_encoder/config.json

@@ -0,0 +1,384 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "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,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "quantization_config": {
+    "add_skip_keys": true,
+    "dequantize_fp32": true,
+    "dynamic_loss_threshold": 0.01,
+    "group_size": 0,
+    "is_integer": true,
+    "is_training": false,
+    "modules_dtype_dict": {
+      "int5": [
+        "model.layers.0.mlp.down_proj.weight",
+        "model.layers.1.mlp.down_proj.weight",
+        "model.layers.2.mlp.down_proj.weight",
+        "model.layers.3.mlp.down_proj.weight",
+        "model.layers.4.mlp.up_proj.weight",
+        "model.layers.4.mlp.down_proj.weight",
+        "model.layers.5.mlp.up_proj.weight",
+        "model.layers.5.mlp.down_proj.weight",
+        "model.layers.6.self_attn.v_proj.weight",
+        "model.layers.6.mlp.up_proj.weight",
+        "model.layers.6.mlp.down_proj.weight",
+        "model.layers.7.mlp.up_proj.weight",
+        "model.layers.7.mlp.down_proj.weight",
+        "model.layers.8.mlp.up_proj.weight",
+        "model.layers.8.mlp.down_proj.weight",
+        "model.layers.9.self_attn.k_proj.weight",
+        "model.layers.9.mlp.up_proj.weight",
+        "model.layers.9.mlp.down_proj.weight",
+        "model.layers.10.self_attn.v_proj.weight",
+        "model.layers.10.mlp.up_proj.weight",
+        "model.layers.10.mlp.down_proj.weight",
+        "model.layers.11.self_attn.k_proj.weight",
+        "model.layers.11.mlp.up_proj.weight",
+        "model.layers.11.mlp.down_proj.weight",
+        "model.layers.12.mlp.gate_proj.weight",
+        "model.layers.12.mlp.up_proj.weight",
+        "model.layers.12.mlp.down_proj.weight",
+        "model.layers.13.mlp.gate_proj.weight",
+        "model.layers.13.mlp.up_proj.weight",
+        "model.layers.13.mlp.down_proj.weight",
+        "model.layers.14.mlp.gate_proj.weight",
+        "model.layers.14.mlp.up_proj.weight",
+        "model.layers.14.mlp.down_proj.weight",
+        "model.layers.15.mlp.gate_proj.weight",
+        "model.layers.15.mlp.up_proj.weight",
+        "model.layers.15.mlp.down_proj.weight",
+        "model.layers.16.mlp.gate_proj.weight",
+        "model.layers.16.mlp.up_proj.weight",
+        "model.layers.16.mlp.down_proj.weight",
+        "model.layers.17.mlp.gate_proj.weight",
+        "model.layers.17.mlp.up_proj.weight",
+        "model.layers.17.mlp.down_proj.weight",
+        "model.layers.18.mlp.gate_proj.weight",
+        "model.layers.18.mlp.up_proj.weight",
+        "model.layers.18.mlp.down_proj.weight",
+        "model.layers.19.self_attn.k_proj.weight",
+        "model.layers.19.self_attn.v_proj.weight",
+        "model.layers.19.mlp.gate_proj.weight",
+        "model.layers.19.mlp.up_proj.weight",
+        "model.layers.19.mlp.down_proj.weight",
+        "model.layers.20.self_attn.v_proj.weight",
+        "model.layers.20.mlp.gate_proj.weight",
+        "model.layers.20.mlp.up_proj.weight",
+        "model.layers.20.mlp.down_proj.weight",
+        "model.layers.21.self_attn.v_proj.weight",
+        "model.layers.21.mlp.gate_proj.weight",
+        "model.layers.21.mlp.up_proj.weight",
+        "model.layers.21.mlp.down_proj.weight",
+        "model.layers.22.self_attn.v_proj.weight",
+        "model.layers.22.mlp.gate_proj.weight",
+        "model.layers.22.mlp.up_proj.weight",
+        "model.layers.22.mlp.down_proj.weight",
+        "model.layers.23.self_attn.v_proj.weight",
+        "model.layers.23.mlp.gate_proj.weight",
+        "model.layers.23.mlp.up_proj.weight",
+        "model.layers.23.mlp.down_proj.weight",
+        "model.layers.24.self_attn.v_proj.weight",
+        "model.layers.24.mlp.gate_proj.weight",
+        "model.layers.24.mlp.up_proj.weight",
+        "model.layers.24.mlp.down_proj.weight",
+        "model.layers.25.self_attn.v_proj.weight",
+        "model.layers.25.mlp.gate_proj.weight",
+        "model.layers.25.mlp.up_proj.weight",
+        "model.layers.25.mlp.down_proj.weight",
+        "model.layers.26.self_attn.v_proj.weight",
+        "model.layers.26.mlp.gate_proj.weight",
+        "model.layers.26.mlp.up_proj.weight",
+        "model.layers.26.mlp.down_proj.weight",
+        "model.layers.27.self_attn.v_proj.weight",
+        "model.layers.27.mlp.gate_proj.weight",
+        "model.layers.27.mlp.up_proj.weight",
+        "model.layers.27.mlp.down_proj.weight",
+        "model.layers.28.mlp.gate_proj.weight",
+        "model.layers.28.mlp.up_proj.weight",
+        "model.layers.28.mlp.down_proj.weight",
+        "model.layers.29.self_attn.v_proj.weight",
+        "model.layers.30.self_attn.v_proj.weight",
+        "model.layers.31.self_attn.v_proj.weight",
+        "model.layers.32.self_attn.v_proj.weight",
+        "model.layers.33.self_attn.v_proj.weight",
+        "model.layers.34.self_attn.v_proj.weight",
+        "model.layers.34.mlp.down_proj.weight",
+        "model.layers.35.self_attn.v_proj.weight",
+        "model.layers.35.mlp.down_proj.weight"
+      ],
+      "uint4": [
+        "model.layers.0.self_attn.q_proj.weight",
+        "model.layers.0.self_attn.k_proj.weight",
+        "model.layers.0.self_attn.v_proj.weight",
+        "model.layers.0.self_attn.o_proj.weight",
+        "model.layers.0.mlp.gate_proj.weight",
+        "model.layers.0.mlp.up_proj.weight",
+        "model.layers.1.self_attn.q_proj.weight",
+        "model.layers.1.self_attn.k_proj.weight",
+        "model.layers.1.self_attn.v_proj.weight",
+        "model.layers.1.self_attn.o_proj.weight",
+        "model.layers.1.mlp.gate_proj.weight",
+        "model.layers.1.mlp.up_proj.weight",
+        "model.layers.2.self_attn.q_proj.weight",
+        "model.layers.2.self_attn.k_proj.weight",
+        "model.layers.2.self_attn.v_proj.weight",
+        "model.layers.2.self_attn.o_proj.weight",
+        "model.layers.2.mlp.gate_proj.weight",
+        "model.layers.2.mlp.up_proj.weight",
+        "model.layers.3.self_attn.q_proj.weight",
+        "model.layers.3.self_attn.k_proj.weight",
+        "model.layers.3.self_attn.v_proj.weight",
+        "model.layers.3.self_attn.o_proj.weight",
+        "model.layers.3.mlp.gate_proj.weight",
+        "model.layers.3.mlp.up_proj.weight",
+        "model.layers.4.self_attn.q_proj.weight",
+        "model.layers.4.self_attn.k_proj.weight",
+        "model.layers.4.self_attn.v_proj.weight",
+        "model.layers.4.self_attn.o_proj.weight",
+        "model.layers.4.mlp.gate_proj.weight",
+        "model.layers.5.self_attn.q_proj.weight",
+        "model.layers.5.self_attn.k_proj.weight",
+        "model.layers.5.self_attn.v_proj.weight",
+        "model.layers.5.self_attn.o_proj.weight",
+        "model.layers.5.mlp.gate_proj.weight",
+        "model.layers.6.self_attn.q_proj.weight",
+        "model.layers.6.self_attn.k_proj.weight",
+        "model.layers.6.self_attn.o_proj.weight",
+        "model.layers.6.mlp.gate_proj.weight",
+        "model.layers.7.self_attn.q_proj.weight",
+        "model.layers.7.self_attn.k_proj.weight",
+        "model.layers.7.self_attn.v_proj.weight",
+        "model.layers.7.self_attn.o_proj.weight",
+        "model.layers.7.mlp.gate_proj.weight",
+        "model.layers.8.self_attn.q_proj.weight",
+        "model.layers.8.self_attn.k_proj.weight",
+        "model.layers.8.self_attn.v_proj.weight",
+        "model.layers.8.self_attn.o_proj.weight",
+        "model.layers.8.mlp.gate_proj.weight",
+        "model.layers.9.self_attn.q_proj.weight",
+        "model.layers.9.self_attn.v_proj.weight",
+        "model.layers.9.self_attn.o_proj.weight",
+        "model.layers.9.mlp.gate_proj.weight",
+        "model.layers.10.self_attn.q_proj.weight",
+        "model.layers.10.self_attn.k_proj.weight",
+        "model.layers.10.self_attn.o_proj.weight",
+        "model.layers.10.mlp.gate_proj.weight",
+        "model.layers.11.self_attn.q_proj.weight",
+        "model.layers.11.self_attn.v_proj.weight",
+        "model.layers.11.self_attn.o_proj.weight",
+        "model.layers.11.mlp.gate_proj.weight",
+        "model.layers.12.self_attn.q_proj.weight",
+        "model.layers.12.self_attn.k_proj.weight",
+        "model.layers.12.self_attn.v_proj.weight",
+        "model.layers.12.self_attn.o_proj.weight",
+        "model.layers.13.self_attn.q_proj.weight",
+        "model.layers.13.self_attn.k_proj.weight",
+        "model.layers.13.self_attn.v_proj.weight",
+        "model.layers.13.self_attn.o_proj.weight",
+        "model.layers.14.self_attn.q_proj.weight",
+        "model.layers.14.self_attn.k_proj.weight",
+        "model.layers.14.self_attn.v_proj.weight",
+        "model.layers.14.self_attn.o_proj.weight",
+        "model.layers.15.self_attn.q_proj.weight",
+        "model.layers.15.self_attn.k_proj.weight",
+        "model.layers.15.self_attn.v_proj.weight",
+        "model.layers.15.self_attn.o_proj.weight",
+        "model.layers.16.self_attn.q_proj.weight",
+        "model.layers.16.self_attn.k_proj.weight",
+        "model.layers.16.self_attn.v_proj.weight",
+        "model.layers.16.self_attn.o_proj.weight",
+        "model.layers.17.self_attn.q_proj.weight",
+        "model.layers.17.self_attn.k_proj.weight",
+        "model.layers.17.self_attn.v_proj.weight",
+        "model.layers.17.self_attn.o_proj.weight",
+        "model.layers.18.self_attn.q_proj.weight",
+        "model.layers.18.self_attn.k_proj.weight",
+        "model.layers.18.self_attn.v_proj.weight",
+        "model.layers.18.self_attn.o_proj.weight",
+        "model.layers.19.self_attn.q_proj.weight",
+        "model.layers.19.self_attn.o_proj.weight",
+        "model.layers.20.self_attn.q_proj.weight",
+        "model.layers.20.self_attn.k_proj.weight",
+        "model.layers.20.self_attn.o_proj.weight",
+        "model.layers.21.self_attn.q_proj.weight",
+        "model.layers.21.self_attn.k_proj.weight",
+        "model.layers.21.self_attn.o_proj.weight",
+        "model.layers.22.self_attn.q_proj.weight",
+        "model.layers.22.self_attn.k_proj.weight",
+        "model.layers.22.self_attn.o_proj.weight",
+        "model.layers.23.self_attn.q_proj.weight",
+        "model.layers.23.self_attn.k_proj.weight",
+        "model.layers.23.self_attn.o_proj.weight",
+        "model.layers.24.self_attn.q_proj.weight",
+        "model.layers.24.self_attn.k_proj.weight",
+        "model.layers.24.self_attn.o_proj.weight",
+        "model.layers.25.self_attn.q_proj.weight",
+        "model.layers.25.self_attn.k_proj.weight",
+        "model.layers.25.self_attn.o_proj.weight",
+        "model.layers.26.self_attn.q_proj.weight",
+        "model.layers.26.self_attn.k_proj.weight",
+        "model.layers.26.self_attn.o_proj.weight",
+        "model.layers.27.self_attn.q_proj.weight",
+        "model.layers.27.self_attn.k_proj.weight",
+        "model.layers.27.self_attn.o_proj.weight",
+        "model.layers.28.self_attn.q_proj.weight",
+        "model.layers.28.self_attn.k_proj.weight",
+        "model.layers.28.self_attn.v_proj.weight",
+        "model.layers.28.self_attn.o_proj.weight",
+        "model.layers.29.self_attn.q_proj.weight",
+        "model.layers.29.self_attn.k_proj.weight",
+        "model.layers.29.self_attn.o_proj.weight",
+        "model.layers.29.mlp.gate_proj.weight",
+        "model.layers.29.mlp.up_proj.weight",
+        "model.layers.29.mlp.down_proj.weight",
+        "model.layers.30.self_attn.q_proj.weight",
+        "model.layers.30.self_attn.k_proj.weight",
+        "model.layers.30.self_attn.o_proj.weight",
+        "model.layers.30.mlp.gate_proj.weight",
+        "model.layers.30.mlp.up_proj.weight",
+        "model.layers.30.mlp.down_proj.weight",
+        "model.layers.31.self_attn.q_proj.weight",
+        "model.layers.31.self_attn.k_proj.weight",
+        "model.layers.31.self_attn.o_proj.weight",
+        "model.layers.31.mlp.gate_proj.weight",
+        "model.layers.31.mlp.up_proj.weight",
+        "model.layers.31.mlp.down_proj.weight",
+        "model.layers.32.self_attn.q_proj.weight",
+        "model.layers.32.self_attn.k_proj.weight",
+        "model.layers.32.self_attn.o_proj.weight",
+        "model.layers.32.mlp.gate_proj.weight",
+        "model.layers.32.mlp.up_proj.weight",
+        "model.layers.32.mlp.down_proj.weight",
+        "model.layers.33.self_attn.q_proj.weight",
+        "model.layers.33.self_attn.k_proj.weight",
+        "model.layers.33.self_attn.o_proj.weight",
+        "model.layers.33.mlp.gate_proj.weight",
+        "model.layers.33.mlp.up_proj.weight",
+        "model.layers.33.mlp.down_proj.weight",
+        "model.layers.34.self_attn.q_proj.weight",
+        "model.layers.34.self_attn.k_proj.weight",
+        "model.layers.34.self_attn.o_proj.weight",
+        "model.layers.34.mlp.gate_proj.weight",
+        "model.layers.34.mlp.up_proj.weight",
+        "model.layers.35.self_attn.q_proj.weight",
+        "model.layers.35.self_attn.k_proj.weight",
+        "model.layers.35.self_attn.o_proj.weight",
+        "model.layers.35.mlp.gate_proj.weight",
+        "model.layers.35.mlp.up_proj.weight"
+      ]
+    },
+    "modules_quant_config": {},
+    "modules_to_not_convert": [
+      ".emb_out",
+      "multi_modal_projector",
+      ".vid_in",
+      ".time_embed",
+      "patch_emb",
+      ".context_embedder",
+      ".norm_out",
+      "patch_embedding",
+      "wte",
+      ".x_embedder",
+      "patch_embed",
+      ".txt_in",
+      "time_text_embed",
+      "lm_head",
+      ".t_embedder",
+      ".final_layer",
+      ".img_in",
+      ".condition_embedder",
+      ".txt_out",
+      ".vid_out",
+      ".proj_out",
+      "lm_head.weight",
+      ".emb_in",
+      "model.embed_tokens.weight",
+      ".y_embedder",
+      ".img_out"
+    ],
+    "non_blocking": false,
+    "quant_conv": false,
+    "quant_embedding": false,
+    "quant_method": "sdnq",
+    "quantization_device": "cuda",
+    "quantized_matmul_dtype": null,
+    "return_device": "cpu",
+    "sdnq_version": "0.1.8",
+    "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": true,
+    "weights_dtype": "uint2"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

text_encoder/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "5.8.0",
+  "use_cache": true
+}

text_encoder/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c2d6366ab85c90786ccdd829cd2b9e7d30ef3b2ebbb998280e7e4014b542ff
+size 1244659840

text_encoder/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0252d7936260005d7b4f25a96ca433c443beea473b5d2632039d5a4b8ff7fe6f
+size 1992430552

text_encoder/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13636cc41fd99c57a26d640808a4b6b9f337c5de37bc0de1ba06f40832c0c8be
+size 1981357224

text_encoder/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba06c5b2d0a3ae32aa89554ca4decbcf53c037bcbfafd137138719e7885c9f1
+size 1647147512