Show verified image/video examples and actual model structures

README.md

@@ -60,22 +60,31 @@ sglang serve \
 - Transformers (✅ verified)
 
 ```python
+import numpy as np
 import torch
 from PIL import Image
 from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
+from transformers.video_utils import VideoMetadata
 
 model_id = "tiny-random/qwen3.8"
 model = Qwen3_5ForConditionalGeneration.from_pretrained(
     model_id, dtype=torch.bfloat16, device_map="cuda", attn_implementation="sdpa",
 )
 processor = AutoProcessor.from_pretrained(model_id)
+image = Image.new("RGB", (64, 64), (220, 30, 30))
+# Four predecoded RGB frames, with timestamps supplied through video_metadata.
+video = np.stack([np.asarray(Image.new("RGB", (64, 64), color)) for color in
+                  [(220, 30, 30), (30, 220, 30), (30, 30, 220), (220, 220, 30)]])
 messages = [{"role": "user", "content": [
-    {"type": "image", "image": Image.new("RGB", (64, 64), (220, 30, 30))},
-    {"type": "text", "text": "Describe this image."},
+    {"type": "image", "image": image},
+    {"type": "video", "video": video},
+    {"type": "text", "text": "Describe the image and the video."},
 ]}]
 inputs = processor.apply_chat_template(
     messages, tokenize=True, add_generation_prompt=True,
     return_dict=True, return_tensors="pt",
+    do_sample_frames=False,
+    video_metadata=[VideoMetadata(total_num_frames=4, fps=2, frames_indices=[0, 1, 2, 3])],
 ).to(model.device)
 output = model.generate(**inputs, do_sample=False, max_new_tokens=10)
 print(processor.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
@@ -159,7 +168,146 @@ for name in sorted(set(list_repo_files(source_model_id, revision=source_revision
 <details><summary>Click to expand</summary>
 
 ```text
-Qwen3.8 VL: 8 backbone layers + 1 MTP layer; hidden_size=16
+Qwen3_5ForConditionalGeneration(
+  (model): Qwen3_5Model(
+    (visual): Qwen3_5VisionModel(
+      (patch_embed): Qwen3_5VisionPatchEmbed(
+        (proj): Conv3d(3, 64, kernel_size=(2, 16, 16), stride=(2, 16, 16))
+      )
+      (pos_embed): Embedding(2304, 64)
+      (rotary_pos_emb): Qwen3_5VisionRotaryEmbedding()
+      (blocks): ModuleList(
+        (0-1): 2 x Qwen3_5VisionBlock(
+          (norm1): LayerNorm((64,), eps=1e-06, elementwise_affine=True, bias=True)
+          (norm2): LayerNorm((64,), eps=1e-06, elementwise_affine=True, bias=True)
+          (attn): Qwen3_5VisionAttention(
+            (qkv): Linear(in_features=64, out_features=192, bias=True)
+            (proj): Linear(in_features=64, out_features=64, bias=True)
+          )
+          (mlp): Qwen3_5VisionMLP(
+            (linear_fc1): Linear(in_features=64, out_features=128, bias=True)
+            (linear_fc2): Linear(in_features=128, out_features=64, bias=True)
+            (act_fn): GELUTanh()
+          )
+        )
+      )
+      (merger): Qwen3_5VisionPatchMerger(
+        (norm): LayerNorm((64,), eps=1e-06, elementwise_affine=True, bias=True)
+        (linear_fc1): Linear(in_features=256, out_features=256, bias=True)
+        (act_fn): GELU(approximate='none')
+        (linear_fc2): Linear(in_features=256, out_features=16, bias=True)
+      )
+    )
+    (language_model): Qwen3_5TextModel(
+      (embed_tokens): Embedding(248320, 16)
+      (layers): ModuleList(
+        (0-2): 3 x Qwen3_5DecoderLayer(
+          (linear_attn): Qwen3_5GatedDeltaNet(
+            (conv1d): Conv1d(1280, 1280, kernel_size=(4,), stride=(1,), padding=(3,), groups=1280, bias=False)
+            (norm): Qwen3_5RMSNormGated()
+            (out_proj): Linear(in_features=768, out_features=16, bias=False)
+            (in_proj_qkv): Linear(in_features=16, out_features=1280, bias=False)
+            (in_proj_z): Linear(in_features=16, out_features=768, bias=False)
+            (in_proj_b): Linear(in_features=16, out_features=6, bias=False)
+            (in_proj_a): Linear(in_features=16, out_features=6, bias=False)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=512, bias=False)
+            (up_proj): Linear(in_features=16, out_features=512, bias=False)
+            (down_proj): Linear(in_features=512, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+        (3): Qwen3_5DecoderLayer(
+          (self_attn): Qwen3_5Attention(
+            (q_proj): Linear(in_features=16, out_features=3072, bias=False)
+            (k_proj): Linear(in_features=16, out_features=256, bias=False)
+            (v_proj): Linear(in_features=16, out_features=256, bias=False)
+            (o_proj): Linear(in_features=1536, out_features=16, bias=False)
+            (q_norm): Qwen3_5RMSNorm((128,), eps=1e-06)
+            (k_norm): Qwen3_5RMSNorm((128,), eps=1e-06)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=512, bias=False)
+            (up_proj): Linear(in_features=16, out_features=512, bias=False)
+            (down_proj): Linear(in_features=512, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+        (4-6): 3 x Qwen3_5DecoderLayer(
+          (linear_attn): Qwen3_5GatedDeltaNet(
+            (conv1d): Conv1d(1280, 1280, kernel_size=(4,), stride=(1,), padding=(3,), groups=1280, bias=False)
+            (norm): Qwen3_5RMSNormGated()
+            (out_proj): Linear(in_features=768, out_features=16, bias=False)
+            (in_proj_qkv): Linear(in_features=16, out_features=1280, bias=False)
+            (in_proj_z): Linear(in_features=16, out_features=768, bias=False)
+            (in_proj_b): Linear(in_features=16, out_features=6, bias=False)
+            (in_proj_a): Linear(in_features=16, out_features=6, bias=False)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=512, bias=False)
+            (up_proj): Linear(in_features=16, out_features=512, bias=False)
+            (down_proj): Linear(in_features=512, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+        (7): Qwen3_5DecoderLayer(
+          (self_attn): Qwen3_5Attention(
+            (q_proj): Linear(in_features=16, out_features=3072, bias=False)
+            (k_proj): Linear(in_features=16, out_features=256, bias=False)
+            (v_proj): Linear(in_features=16, out_features=256, bias=False)
+            (o_proj): Linear(in_features=1536, out_features=16, bias=False)
+            (q_norm): Qwen3_5RMSNorm((128,), eps=1e-06)
+            (k_norm): Qwen3_5RMSNorm((128,), eps=1e-06)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=512, bias=False)
+            (up_proj): Linear(in_features=16, out_features=512, bias=False)
+            (down_proj): Linear(in_features=512, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+      )
+      (norm): Qwen3_5RMSNorm((16,), eps=1e-06)
+      (rotary_emb): Qwen3_5TextRotaryEmbedding()
+    )
+  )
+  (lm_head): Linear(in_features=16, out_features=248320, bias=False)
+  (mtp): ModuleDict(
+    (pre_fc_norm_embedding): Qwen3_5RMSNorm((16,), eps=1e-06)
+    (pre_fc_norm_hidden): Qwen3_5RMSNorm((16,), eps=1e-06)
+    (fc): Linear(in_features=32, out_features=16, bias=False)
+    (layers): ModuleList(
+      (0): Qwen3_5DecoderLayer(
+        (self_attn): Qwen3_5Attention(
+          (q_proj): Linear(in_features=16, out_features=3072, bias=False)
+          (k_proj): Linear(in_features=16, out_features=256, bias=False)
+          (v_proj): Linear(in_features=16, out_features=256, bias=False)
+          (o_proj): Linear(in_features=1536, out_features=16, bias=False)
+          (q_norm): Qwen3_5RMSNorm((128,), eps=1e-06)
+          (k_norm): Qwen3_5RMSNorm((128,), eps=1e-06)
+        )
+        (mlp): Qwen3_5MLP(
+          (gate_proj): Linear(in_features=16, out_features=512, bias=False)
+          (up_proj): Linear(in_features=16, out_features=512, bias=False)
+          (down_proj): Linear(in_features=512, out_features=16, bias=False)
+          (act_fn): SiLUActivation()
+        )
+        (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+      )
+    )
+    (norm): Qwen3_5RMSNorm((16,), eps=1e-06)
+  )
+)
 ```
 
 </details>