noctis/AICASGC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

模型结构

Browse Source
This commit is contained in:
noctis
2026-02-25 14:36:52 +08:00
parent d6aa5f568a
commit 902b0373a4
3 changed files with 69 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@ -1,2 +1,3 @@
data/*
Qwen3-VL-2B-Instruct/*
Qwen3-VL-2B-Instruct/*
__pycache__

66
README_CN.md
View File

@ -346,3 +346,69 @@ python benchmark.py \
Qwen3VLForConditionalGeneration(
(model): Qwen3VLModel(
(visual): Qwen3VLVisionModel(
(patch_embed): Qwen3VLVisionPatchEmbed(
(proj): Conv3d(3, 1024, kernel_size=(2, 16, 16), stride=(2, 16, 16))
)
(pos_embed): Embedding(2304, 1024)
(rotary_pos_emb): Qwen3VLVisionRotaryEmbedding()
(blocks): ModuleList(
(0-23): 24 x Qwen3VLVisionBlock(
(norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
(norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
(attn): Qwen3VLVisionAttention(
(qkv): Linear(in_features=1024, out_features=3072, bias=True)
(proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(mlp): Qwen3VLVisionMLP(
(linear_fc1): Linear(in_features=1024, out_features=4096, bias=True)
(linear_fc2): Linear(in_features=4096, out_features=1024, bias=True)
(act_fn): GELUTanh()
)
)
)
(merger): Qwen3VLVisionPatchMerger(
(norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
(linear_fc1): Linear(in_features=4096, out_features=4096, bias=True)
(act_fn): GELU(approximate='none')
(linear_fc2): Linear(in_features=4096, out_features=2048, bias=True)
)
(deepstack_merger_list): ModuleList(
(0-2): 3 x Qwen3VLVisionPatchMerger(
(norm): LayerNorm((4096,), eps=1e-06, elementwise_affine=True)
(linear_fc1): Linear(in_features=4096, out_features=4096, bias=True)
(act_fn): GELU(approximate='none')
(linear_fc2): Linear(in_features=4096, out_features=2048, bias=True)
)
)
)
(language_model): Qwen3VLTextModel(
(embed_tokens): Embedding(151936, 2048)
(layers): ModuleList(
(0-27): 28 x Qwen3VLTextDecoderLayer(
(self_attn): Qwen3VLTextAttention(
(q_proj): Linear(in_features=2048, out_features=2048, bias=False)
(k_proj): Linear(in_features=2048, out_features=1024, bias=False)
(v_proj): Linear(in_features=2048, out_features=1024, bias=False)
(o_proj): Linear(in_features=2048, out_features=2048, bias=False)
(q_norm): Qwen3VLTextRMSNorm((128,), eps=1e-06)
(k_norm): Qwen3VLTextRMSNorm((128,), eps=1e-06)
)
(mlp): Qwen3VLTextMLP(
(gate_proj): Linear(in_features=2048, out_features=6144, bias=False)
(up_proj): Linear(in_features=2048, out_features=6144, bias=False)
(down_proj): Linear(in_features=6144, out_features=2048, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): Qwen3VLTextRMSNorm((2048,), eps=1e-06)
(post_attention_layernorm): Qwen3VLTextRMSNorm((2048,), eps=1e-06)
)
)
(norm): Qwen3VLTextRMSNorm((2048,), eps=1e-06)
(rotary_emb): Qwen3VLTextRotaryEmbedding()
)
)
(lm_head): Linear(in_features=2048, out_features=151936, bias=False)
)

2
benchmark.py
View File

@ -588,7 +588,7 @@ def main():
parser.add_argument("--model-path", type=str, default="./Qwen3-VL-2B-Instruct", help="Path to model weights")
parser.add_argument("--dataset-path", type=str, default="./data", help="Path to validation dataset")
parser.add_argument("--output", type=str, default="result.json", help="Output JSON file path")
parser.add_argument("--num-samples", type=int, default=None, help="Number of samples to evaluate (default: all)")
parser.add_argument("--num-samples", type=int, default=100, help="Number of samples to evaluate (default: all)")
parser.add_argument("--random-seed", type=int, default=None, help="Random seed for reproducibility")
args = parser.parse_args()