Upload content from Colab

.gitattributes

@@ -1 +1,4 @@
 language_model/lm_head.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,386 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "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.language_model.layers.0.mlp.down_proj.weight",
+        "model.language_model.layers.1.mlp.down_proj.weight",
+        "model.language_model.layers.2.mlp.down_proj.weight",
+        "model.language_model.layers.3.mlp.down_proj.weight",
+        "model.language_model.layers.4.mlp.down_proj.weight",
+        "model.language_model.layers.9.mlp.up_proj.weight",
+        "model.language_model.layers.10.mlp.up_proj.weight",
+        "model.language_model.layers.11.mlp.up_proj.weight",
+        "model.language_model.layers.12.self_attn.v_proj.weight",
+        "model.language_model.layers.12.mlp.up_proj.weight",
+        "model.language_model.layers.12.mlp.down_proj.weight",
+        "model.language_model.layers.13.mlp.up_proj.weight",
+        "model.language_model.layers.13.mlp.down_proj.weight",
+        "model.language_model.layers.14.mlp.up_proj.weight",
+        "model.language_model.layers.14.mlp.down_proj.weight",
+        "model.language_model.layers.15.mlp.up_proj.weight",
+        "model.language_model.layers.15.mlp.down_proj.weight",
+        "model.language_model.layers.16.mlp.up_proj.weight",
+        "model.language_model.layers.16.mlp.down_proj.weight",
+        "model.language_model.layers.17.mlp.up_proj.weight",
+        "model.language_model.layers.17.mlp.down_proj.weight",
+        "model.language_model.layers.18.mlp.up_proj.weight",
+        "model.language_model.layers.18.mlp.down_proj.weight",
+        "model.language_model.layers.19.mlp.up_proj.weight",
+        "model.language_model.layers.19.mlp.down_proj.weight",
+        "model.language_model.layers.20.mlp.up_proj.weight",
+        "model.language_model.layers.20.mlp.down_proj.weight",
+        "model.language_model.layers.21.mlp.gate_proj.weight",
+        "model.language_model.layers.21.mlp.down_proj.weight",
+        "model.language_model.layers.22.mlp.gate_proj.weight",
+        "model.language_model.layers.22.mlp.down_proj.weight",
+        "model.language_model.layers.23.self_attn.v_proj.weight",
+        "model.language_model.layers.23.mlp.gate_proj.weight",
+        "model.language_model.layers.23.mlp.up_proj.weight",
+        "model.language_model.layers.24.self_attn.v_proj.weight",
+        "model.language_model.layers.34.mlp.down_proj.weight",
+        "model.language_model.layers.35.mlp.down_proj.weight"
+      ],
+      "int8": [
+        "lm_head"
+      ],
+      "uint4": [
+        "model.language_model.layers.0.self_attn.q_proj.weight",
+        "model.language_model.layers.0.self_attn.k_proj.weight",
+        "model.language_model.layers.0.self_attn.v_proj.weight",
+        "model.language_model.layers.0.self_attn.o_proj.weight",
+        "model.language_model.layers.0.mlp.gate_proj.weight",
+        "model.language_model.layers.0.mlp.up_proj.weight",
+        "model.language_model.layers.1.self_attn.q_proj.weight",
+        "model.language_model.layers.1.self_attn.k_proj.weight",
+        "model.language_model.layers.1.self_attn.v_proj.weight",
+        "model.language_model.layers.1.self_attn.o_proj.weight",
+        "model.language_model.layers.1.mlp.gate_proj.weight",
+        "model.language_model.layers.1.mlp.up_proj.weight",
+        "model.language_model.layers.2.self_attn.q_proj.weight",
+        "model.language_model.layers.2.self_attn.k_proj.weight",
+        "model.language_model.layers.2.self_attn.v_proj.weight",
+        "model.language_model.layers.2.self_attn.o_proj.weight",
+        "model.language_model.layers.2.mlp.gate_proj.weight",
+        "model.language_model.layers.2.mlp.up_proj.weight",
+        "model.language_model.layers.3.self_attn.q_proj.weight",
+        "model.language_model.layers.3.self_attn.k_proj.weight",
+        "model.language_model.layers.3.self_attn.v_proj.weight",
+        "model.language_model.layers.3.self_attn.o_proj.weight",
+        "model.language_model.layers.3.mlp.gate_proj.weight",
+        "model.language_model.layers.3.mlp.up_proj.weight",
+        "model.language_model.layers.4.self_attn.q_proj.weight",
+        "model.language_model.layers.4.self_attn.k_proj.weight",
+        "model.language_model.layers.4.self_attn.v_proj.weight",
+        "model.language_model.layers.4.self_attn.o_proj.weight",
+        "model.language_model.layers.4.mlp.gate_proj.weight",
+        "model.language_model.layers.4.mlp.up_proj.weight",
+        "model.language_model.layers.5.self_attn.q_proj.weight",
+        "model.language_model.layers.5.self_attn.k_proj.weight",
+        "model.language_model.layers.5.self_attn.v_proj.weight",
+        "model.language_model.layers.5.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.6.self_attn.q_proj.weight",
+        "model.language_model.layers.6.self_attn.k_proj.weight",
+        "model.language_model.layers.6.self_attn.v_proj.weight",
+        "model.language_model.layers.6.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.7.self_attn.q_proj.weight",
+        "model.language_model.layers.7.self_attn.k_proj.weight",
+        "model.language_model.layers.7.self_attn.v_proj.weight",
+        "model.language_model.layers.7.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.8.self_attn.q_proj.weight",
+        "model.language_model.layers.8.self_attn.k_proj.weight",
+        "model.language_model.layers.8.self_attn.v_proj.weight",
+        "model.language_model.layers.8.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.9.self_attn.q_proj.weight",
+        "model.language_model.layers.9.self_attn.k_proj.weight",
+        "model.language_model.layers.9.self_attn.v_proj.weight",
+        "model.language_model.layers.9.self_attn.o_proj.weight",
+        "model.language_model.layers.9.mlp.gate_proj.weight",
+        "model.language_model.layers.9.mlp.down_proj.weight",
+        "model.language_model.layers.10.self_attn.q_proj.weight",
+        "model.language_model.layers.10.self_attn.k_proj.weight",
+        "model.language_model.layers.10.self_attn.v_proj.weight",
+        "model.language_model.layers.10.self_attn.o_proj.weight",
+        "model.language_model.layers.10.mlp.gate_proj.weight",
+        "model.language_model.layers.10.mlp.down_proj.weight",
+        "model.language_model.layers.11.self_attn.q_proj.weight",
+        "model.language_model.layers.11.self_attn.k_proj.weight",
+        "model.language_model.layers.11.self_attn.v_proj.weight",
+        "model.language_model.layers.11.self_attn.o_proj.weight",
+        "model.language_model.layers.11.mlp.gate_proj.weight",
+        "model.language_model.layers.11.mlp.down_proj.weight",
+        "model.language_model.layers.12.self_attn.q_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.mlp.gate_proj.weight",
+        "model.language_model.layers.13.self_attn.q_proj.weight",
+        "model.language_model.layers.13.self_attn.k_proj.weight",
+        "model.language_model.layers.13.self_attn.v_proj.weight",
+        "model.language_model.layers.13.self_attn.o_proj.weight",
+        "model.language_model.layers.13.mlp.gate_proj.weight",
+        "model.language_model.layers.14.self_attn.q_proj.weight",
+        "model.language_model.layers.14.self_attn.k_proj.weight",
+        "model.language_model.layers.14.self_attn.v_proj.weight",
+        "model.language_model.layers.14.self_attn.o_proj.weight",
+        "model.language_model.layers.14.mlp.gate_proj.weight",
+        "model.language_model.layers.15.self_attn.q_proj.weight",
+        "model.language_model.layers.15.self_attn.k_proj.weight",
+        "model.language_model.layers.15.self_attn.v_proj.weight",
+        "model.language_model.layers.15.self_attn.o_proj.weight",
+        "model.language_model.layers.15.mlp.gate_proj.weight",
+        "model.language_model.layers.16.self_attn.q_proj.weight",
+        "model.language_model.layers.16.self_attn.k_proj.weight",
+        "model.language_model.layers.16.self_attn.v_proj.weight",
+        "model.language_model.layers.16.self_attn.o_proj.weight",
+        "model.language_model.layers.16.mlp.gate_proj.weight",
+        "model.language_model.layers.17.self_attn.q_proj.weight",
+        "model.language_model.layers.17.self_attn.k_proj.weight",
+        "model.language_model.layers.17.self_attn.v_proj.weight",
+        "model.language_model.layers.17.self_attn.o_proj.weight",
+        "model.language_model.layers.17.mlp.gate_proj.weight",
+        "model.language_model.layers.18.self_attn.q_proj.weight",
+        "model.language_model.layers.18.self_attn.k_proj.weight",
+        "model.language_model.layers.18.self_attn.v_proj.weight",
+        "model.language_model.layers.18.self_attn.o_proj.weight",
+        "model.language_model.layers.18.mlp.gate_proj.weight",
+        "model.language_model.layers.19.self_attn.q_proj.weight",
+        "model.language_model.layers.19.self_attn.k_proj.weight",
+        "model.language_model.layers.19.self_attn.v_proj.weight",
+        "model.language_model.layers.19.self_attn.o_proj.weight",
+        "model.language_model.layers.19.mlp.gate_proj.weight",
+        "model.language_model.layers.20.self_attn.q_proj.weight",
+        "model.language_model.layers.20.self_attn.k_proj.weight",
+        "model.language_model.layers.20.self_attn.v_proj.weight",
+        "model.language_model.layers.20.self_attn.o_proj.weight",
+        "model.language_model.layers.20.mlp.gate_proj.weight",
+        "model.language_model.layers.21.self_attn.q_proj.weight",
+        "model.language_model.layers.21.self_attn.k_proj.weight",
+        "model.language_model.layers.21.self_attn.v_proj.weight",
+        "model.language_model.layers.21.self_attn.o_proj.weight",
+        "model.language_model.layers.21.mlp.up_proj.weight",
+        "model.language_model.layers.22.self_attn.q_proj.weight",
+        "model.language_model.layers.22.self_attn.k_proj.weight",
+        "model.language_model.layers.22.self_attn.v_proj.weight",
+        "model.language_model.layers.22.self_attn.o_proj.weight",
+        "model.language_model.layers.22.mlp.up_proj.weight",
+        "model.language_model.layers.23.self_attn.q_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.mlp.down_proj.weight",
+        "model.language_model.layers.24.self_attn.q_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.mlp.gate_proj.weight",
+        "model.language_model.layers.24.mlp.up_proj.weight",
+        "model.language_model.layers.24.mlp.down_proj.weight",
+        "model.language_model.layers.25.self_attn.q_proj.weight",
+        "model.language_model.layers.25.self_attn.k_proj.weight",
+        "model.language_model.layers.25.self_attn.v_proj.weight",
+        "model.language_model.layers.25.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.26.self_attn.q_proj.weight",
+        "model.language_model.layers.26.self_attn.k_proj.weight",
+        "model.language_model.layers.26.self_attn.v_proj.weight",
+        "model.language_model.layers.26.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.27.self_attn.q_proj.weight",
+        "model.language_model.layers.27.self_attn.k_proj.weight",
+        "model.language_model.layers.27.self_attn.v_proj.weight",
+        "model.language_model.layers.27.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.28.self_attn.q_proj.weight",
+        "model.language_model.layers.28.self_attn.k_proj.weight",
+        "model.language_model.layers.28.self_attn.v_proj.weight",
+        "model.language_model.layers.28.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.29.self_attn.q_proj.weight",
+        "model.language_model.layers.29.self_attn.k_proj.weight",
+        "model.language_model.layers.29.self_attn.v_proj.weight",
+        "model.language_model.layers.29.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.30.self_attn.q_proj.weight",
+        "model.language_model.layers.30.self_attn.k_proj.weight",
+        "model.language_model.layers.30.self_attn.v_proj.weight",
+        "model.language_model.layers.30.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.31.self_attn.q_proj.weight",
+        "model.language_model.layers.31.self_attn.k_proj.weight",
+        "model.language_model.layers.31.self_attn.v_proj.weight",
+        "model.language_model.layers.31.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.32.self_attn.q_proj.weight",
+        "model.language_model.layers.32.self_attn.k_proj.weight",
+        "model.language_model.layers.32.self_attn.v_proj.weight",
+        "model.language_model.layers.32.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.33.self_attn.q_proj.weight",
+        "model.language_model.layers.33.self_attn.k_proj.weight",
+        "model.language_model.layers.33.self_attn.v_proj.weight",
+        "model.language_model.layers.33.self_attn.o_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.mlp.down_proj.weight",
+        "model.language_model.layers.34.self_attn.q_proj.weight",
+        "model.language_model.layers.34.self_attn.k_proj.weight",
+        "model.language_model.layers.34.self_attn.v_proj.weight",
+        "model.language_model.layers.34.self_attn.o_proj.weight",
+        "model.language_model.layers.34.mlp.gate_proj.weight",
+        "model.language_model.layers.34.mlp.up_proj.weight",
+        "model.language_model.layers.35.self_attn.q_proj.weight",
+        "model.language_model.layers.35.self_attn.k_proj.weight",
+        "model.language_model.layers.35.self_attn.v_proj.weight",
+        "model.language_model.layers.35.self_attn.o_proj.weight",
+        "model.language_model.layers.35.mlp.gate_proj.weight",
+        "model.language_model.layers.35.mlp.up_proj.weight"
+      ]
+    },
+    "modules_quant_config": {},
+    "modules_to_not_convert": [
+      "lm_head",
+      ".t_embedder",
+      ".vid_in",
+      "multi_modal_projector",
+      ".txt_in",
+      "patch_embed",
+      "t_embedder1",
+      "patch_embedding",
+      ".final_layer",
+      ".time_embed",
+      "time_text_embed",
+      "correction_coefs",
+      ".img_out",
+      ".context_embedder",
+      ".x_embedder",
+      "prediction_coefs",
+      ".txt_out",
+      ".img_in",
+      ".emb_in",
+      ".proj_out",
+      ".emb_out",
+      "wte",
+      "visual",
+      ".norm_out",
+      "embedding_projection",
+      ".condition_embedder",
+      "lm_head.weight",
+      "final_layer2",
+      ".y_embedder",
+      ".vid_out",
+      "x_embedder",
+      "patch_emb"
+    ],
+    "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": 16,
+    "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": "uint4"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "float32",
+    "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": "4.57.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "float32",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56b87c823f3f51d8b127d55ece27a8512ea328d705a7bde872856b81a18f37e
+size 4999690416

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7257c4b8815e911553bba1b349e71196f4eb077358aa5ee51d9fd19b3e975b34
+size 4338534096

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c7495b4a90129d52b02c4d4fd1f8b0dcba8a6f9c99fb7f56098cd8a32675c6
+size 2489319552