theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:48:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

add research tutorial sec 1

Browse Source
This commit is contained in:
Artiprocher
2026-02-02 14:28:26 +08:00
parent 98290190ec
commit 98ab238340
10 changed files with 1679 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
diffsynth/models/z_image_text_encoder.py
View File

@@ -6,6 +6,36 @@ class ZImageTextEncoder(torch.nn.Module):
def __init__(self, model_size="4B"):
super().__init__()
config_dict = {
"0.6B": Qwen3Config(**{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": False,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": None,
"rope_theta": 1000000,
"sliding_window": None,
"tie_word_embeddings": True,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": True,
"use_sliding_window": False,
"vocab_size": 151936
}),
"4B": Qwen3Config(**{
"architectures": [
"Qwen3ForCausalLM"