Training in progress, step 530
Browse files- config.json +62 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ChineseCLIPDualTextModel"
|
| 4 |
+
],
|
| 5 |
+
"initializer_factor": 1.0,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "chinese_clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_attn_implementation_autoset": true,
|
| 12 |
+
"architectures": [
|
| 13 |
+
"ChineseCLIPTextModel"
|
| 14 |
+
],
|
| 15 |
+
"attention_probs_dropout_prob": 0.1,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"directionality": "bidi",
|
| 18 |
+
"eos_token_id": 2,
|
| 19 |
+
"hidden_act": "gelu",
|
| 20 |
+
"hidden_dropout_prob": 0.1,
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"initializer_factor": 1.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "chinese_clip_text_model",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pooler_fc_size": 768,
|
| 32 |
+
"pooler_num_attention_heads": 12,
|
| 33 |
+
"pooler_num_fc_layers": 3,
|
| 34 |
+
"pooler_size_per_head": 128,
|
| 35 |
+
"pooler_type": "first_token_transform",
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
},
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"vision_config": {
|
| 45 |
+
"attention_dropout": 0.0,
|
| 46 |
+
"dropout": 0.0,
|
| 47 |
+
"hidden_act": "quick_gelu",
|
| 48 |
+
"hidden_size": 768,
|
| 49 |
+
"image_size": 224,
|
| 50 |
+
"initializer_factor": 1.0,
|
| 51 |
+
"initializer_range": 0.02,
|
| 52 |
+
"intermediate_size": 3072,
|
| 53 |
+
"layer_norm_eps": 1e-05,
|
| 54 |
+
"model_type": "chinese_clip_vision_model",
|
| 55 |
+
"num_attention_heads": 12,
|
| 56 |
+
"num_channels": 3,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"patch_size": 16,
|
| 59 |
+
"projection_dim": 512,
|
| 60 |
+
"torch_dtype": "float32"
|
| 61 |
+
}
|
| 62 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ab048d8f6fac6ed73cd126ca9c2606393b35617c6950c3a995281ce05c0b351
|
| 3 |
+
size 816611916
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5a88fe9b14099f17116299432809110cb8b21dc35776fa512ed8d878da1931b
|
| 3 |
+
size 5432
|