Spaces:
Running on Zero
Running on Zero
File size: 2,772 Bytes
b347817 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | import torch
from torch import Tensor
class Krea2TextEncoder(torch.nn.Module):
def __init__(self):
super().__init__()
from transformers import Qwen3VLConfig, Qwen3VLForConditionalGeneration
config = Qwen3VLConfig(**{
"architectures": ["Qwen3VLForConditionalGeneration"],
"image_token_id": 151655,
"model_type": "qwen3_vl",
"text_config": {
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"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,
"tie_word_embeddings": True,
"use_cache": True,
"vocab_size": 151936,
},
"tie_word_embeddings": True,
"transformers_version": "4.57.0.dev0",
"video_token_id": 151656,
"vision_config": {
"deepstack_visual_indexes": [5, 11, 17],
"depth": 24,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1024,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4096,
"model_type": "qwen3_vl",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2560,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2,
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
})
self.model = Qwen3VLForConditionalGeneration(config)
self.config = config
def forward(
self,
input_ids=None,
attention_mask=None,
output_hidden_states=True,
**kwargs,
):
outputs = self.model(
input_ids=input_ids,
attention_mask=attention_mask,
output_hidden_states=True,
return_dict=True,
**kwargs,
)
return outputs.hidden_states
|