README.md CHANGED
@@ -1,3 +1,37 @@
1
  ---
 
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language: en
3
  license: mit
4
  ---
5
+ # Kosmos-2.5
6
+
7
+ [Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://github.com/microsoft/unilm/tree/master/kosmos-2.5)
8
+
9
+ ## Model description
10
+
11
+ Kosmos-2.5 is a multimodal literate model for machine reading of text-intensive images. Pre-trained on large-scale text-intensive images, Kosmos-2.5 excels in two distinct yet cooperative transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned its spatial coordinates within the image, and (2) producing structured text output that captures styles and structures into the markdown format. This unified multimodal literate capability is achieved through a shared decoder-only auto-regressive Transformer architecture, task-specific prompts, and flexible text representations. We evaluate Kosmos-2.5 on end-to-end document-level text recognition and image-to-markdown text generation. Furthermore, the model can be readily adapted for any text-intensive image understanding task with different prompts through supervised fine-tuning, making it a general-purpose tool for real-world applications involving text-rich images. This work also paves the way for the future scaling of multimodal large language models.
12
+
13
+ [Kosmos-2.5: A Multimodal Literate Model](https://arxiv.org/abs/2309.11419)
14
+
15
+ ## NOTE:
16
+ Since this is a generative model, there is a risk of **hallucination** during the generation process, and it **CAN NOT** guarantee the accuracy of all OCR/Markdown results in the images.
17
+
18
+ ## Inference
19
+ **Document Understanding Task:** For usage instructions, please refer to [chat.py](chat.py).
20
+
21
+ ## Citation
22
+
23
+ If you find Kosmos-2.5-chat useful in your research, please cite the following paper:
24
+
25
+ ```
26
+ @article{lv2023kosmos,
27
+ title={Kosmos-2.5: A multimodal literate model},
28
+ author={Lv, Tengchao and Huang, Yupan and Chen, Jingye and Cui, Lei and Ma, Shuming and Chang, Yaoyao and Huang, Shaohan and Wang, Wenhui and Dong, Li and Luo, Weiyao and others},
29
+ journal={arXiv preprint arXiv:2309.11419},
30
+ year={2023}
31
+ }
32
+ ```
33
+
34
+ ## License
35
+ The content of this project itself is licensed under the [MIT](https://github.com/microsoft/unilm/blob/master/kosmos-2.5/LICENSE)
36
+
37
+ [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)
chat.py ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import re
2
+ import torch
3
+ import requests
4
+ from PIL import Image, ImageDraw
5
+ from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
6
+
7
+ repo = "microsoft/kosmos-2.5-chat"
8
+ device = "cuda:0"
9
+ dtype = torch.bfloat16
10
+
11
+ model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo,
12
+ device_map=device,
13
+ torch_dtype=dtype,
14
+ attn_implementation="flash_attention_2")
15
+ processor = AutoProcessor.from_pretrained(repo)
16
+
17
+ # sample image
18
+ url = "https://huggingface.co/microsoft/kosmos-2.5/blob/main/receipt_00008.png"
19
+ image = Image.open(requests.get(url, stream=True).raw)
20
+
21
+ question = "What is the sub total of the receipt?"
22
+ template = "<md>A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {} ASSISTANT:"
23
+ prompt = template.format(question)
24
+ inputs = processor(text=prompt, images=image, return_tensors="pt")
25
+
26
+ height, width = inputs.pop("height"), inputs.pop("width")
27
+ raw_width, raw_height = image.size
28
+ scale_height = raw_height / height
29
+ scale_width = raw_width / width
30
+
31
+ inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
32
+ inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
33
+ generated_ids = model.generate(
34
+ **inputs,
35
+ max_new_tokens=1024,
36
+ )
37
+
38
+ generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
39
+ print(generated_text[0])
config.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Kosmos2_5ForConditionalGeneration"
4
+ ],
5
+ "latent_query_num": 2048,
6
+ "model_type": "kosmos-2.5",
7
+ "text_config": {
8
+ "_name_or_path": "",
9
+ "activation_dropout": 0.0,
10
+ "activation_function": "gelu",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "attention_dropout": 0,
14
+ "attention_heads": 16,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "dropout": 0.1,
24
+ "early_stopping": false,
25
+ "embed_dim": 1536,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "ffn_dim": 6144,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-05,
45
+ "layerdrop": 0.0,
46
+ "layers": 24,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 4096,
50
+ "min_length": 0,
51
+ "model_type": "kosmos_2_5_text_model",
52
+ "no_repeat_ngram_size": 3,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "scale_embedding": true,
68
+ "sep_token_id": null,
69
+ "suppress_tokens": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": true,
83
+ "vocab_size": 108481
84
+ },
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.43.3",
87
+ "vision_config": {
88
+ "_name_or_path": "",
89
+ "add_cross_attention": false,
90
+ "architectures": null,
91
+ "attention_dropout": 0.0,
92
+ "bad_words_ids": null,
93
+ "begin_suppress_tokens": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "d_ff": 3968,
98
+ "d_kv": 64,
99
+ "decoder_start_token_id": null,
100
+ "dense_act_fn": "gelu_new",
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout_rate": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_size": 1536,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "initializer_factor": 1.0,
117
+ "initializer_range": 1e-10,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_norm_eps": 1e-06,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "model_type": "kosmos_2_5_vision_model",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 24,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_hidden_layers": 18,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": null,
139
+ "patch_embed_hidden_size": 768,
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "relative_attention_max_distance": 128,
144
+ "relative_attention_num_buckets": 32,
145
+ "remove_invalid_values": false,
146
+ "repetition_penalty": 1.0,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sep_token_id": null,
150
+ "seq_len": 4096,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": null,
161
+ "torchscript": false,
162
+ "typical_p": 1.0,
163
+ "use_bfloat16": false
164
+ }
165
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "no_repeat_ngram_size": 3,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.43.3"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea32f178375c21412ee2829b2389682544ecd6f990a6120b219e065b1500d085
3
+ size 4995252144
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b642fe2ce0ad3ff30838a3daebb6d26252770c65d29306a809e05598fc0e393
3
+ size 503408384
model.safetensors.index.json ADDED
@@ -0,0 +1,621 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5498585088
4
+ },
5
+ "weight_map": {
6
+ "image_to_text_projection.dense.bias": "model-00002-of-00002.safetensors",
7
+ "image_to_text_projection.dense.weight": "model-00002-of-00002.safetensors",
8
+ "image_to_text_projection.latent_query": "model-00002-of-00002.safetensors",
9
+ "image_to_text_projection.x_attn.k_proj.bias": "model-00002-of-00002.safetensors",
10
+ "image_to_text_projection.x_attn.k_proj.weight": "model-00002-of-00002.safetensors",
11
+ "image_to_text_projection.x_attn.out_proj.bias": "model-00002-of-00002.safetensors",
12
+ "image_to_text_projection.x_attn.out_proj.weight": "model-00002-of-00002.safetensors",
13
+ "image_to_text_projection.x_attn.q_proj.bias": "model-00002-of-00002.safetensors",
14
+ "image_to_text_projection.x_attn.q_proj.weight": "model-00002-of-00002.safetensors",
15
+ "image_to_text_projection.x_attn.v_proj.bias": "model-00002-of-00002.safetensors",
16
+ "image_to_text_projection.x_attn.v_proj.weight": "model-00002-of-00002.safetensors",
17
+ "text_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
18
+ "text_model.model.layer_norm.bias": "model-00001-of-00002.safetensors",
19
+ "text_model.model.layer_norm.weight": "model-00001-of-00002.safetensors",
20
+ "text_model.model.layers.0.ffn.fc1.bias": "model-00001-of-00002.safetensors",
21
+ "text_model.model.layers.0.ffn.fc1.weight": "model-00001-of-00002.safetensors",
22
+ "text_model.model.layers.0.ffn.fc2.bias": "model-00001-of-00002.safetensors",
23
+ "text_model.model.layers.0.ffn.fc2.weight": "model-00001-of-00002.safetensors",
24
+ "text_model.model.layers.0.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
25
+ "text_model.model.layers.0.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "text_model.model.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
27
+ "text_model.model.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
28
+ "text_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
29
+ "text_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
30
+ "text_model.model.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
31
+ "text_model.model.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
32
+ "text_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
33
+ "text_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "text_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
35
+ "text_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "text_model.model.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
37
+ "text_model.model.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
38
+ "text_model.model.layers.1.ffn.fc1.bias": "model-00001-of-00002.safetensors",
39
+ "text_model.model.layers.1.ffn.fc1.weight": "model-00001-of-00002.safetensors",
40
+ "text_model.model.layers.1.ffn.fc2.bias": "model-00001-of-00002.safetensors",
41
+ "text_model.model.layers.1.ffn.fc2.weight": "model-00001-of-00002.safetensors",
42
+ "text_model.model.layers.1.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
43
+ "text_model.model.layers.1.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "text_model.model.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
45
+ "text_model.model.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
46
+ "text_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
47
+ "text_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "text_model.model.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
49
+ "text_model.model.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
50
+ "text_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
51
+ "text_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "text_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
53
+ "text_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "text_model.model.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
55
+ "text_model.model.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
56
+ "text_model.model.layers.10.ffn.fc1.bias": "model-00001-of-00002.safetensors",
57
+ "text_model.model.layers.10.ffn.fc1.weight": "model-00001-of-00002.safetensors",
58
+ "text_model.model.layers.10.ffn.fc2.bias": "model-00001-of-00002.safetensors",
59
+ "text_model.model.layers.10.ffn.fc2.weight": "model-00001-of-00002.safetensors",
60
+ "text_model.model.layers.10.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
61
+ "text_model.model.layers.10.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "text_model.model.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
63
+ "text_model.model.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
64
+ "text_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
65
+ "text_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
66
+ "text_model.model.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
67
+ "text_model.model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
68
+ "text_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
69
+ "text_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "text_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
71
+ "text_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "text_model.model.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
73
+ "text_model.model.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
74
+ "text_model.model.layers.11.ffn.fc1.bias": "model-00001-of-00002.safetensors",
75
+ "text_model.model.layers.11.ffn.fc1.weight": "model-00001-of-00002.safetensors",
76
+ "text_model.model.layers.11.ffn.fc2.bias": "model-00001-of-00002.safetensors",
77
+ "text_model.model.layers.11.ffn.fc2.weight": "model-00001-of-00002.safetensors",
78
+ "text_model.model.layers.11.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
79
+ "text_model.model.layers.11.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "text_model.model.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
81
+ "text_model.model.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
82
+ "text_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
83
+ "text_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
84
+ "text_model.model.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
85
+ "text_model.model.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
86
+ "text_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
87
+ "text_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "text_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
89
+ "text_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
90
+ "text_model.model.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
91
+ "text_model.model.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
92
+ "text_model.model.layers.12.ffn.fc1.bias": "model-00001-of-00002.safetensors",
93
+ "text_model.model.layers.12.ffn.fc1.weight": "model-00001-of-00002.safetensors",
94
+ "text_model.model.layers.12.ffn.fc2.bias": "model-00001-of-00002.safetensors",
95
+ "text_model.model.layers.12.ffn.fc2.weight": "model-00001-of-00002.safetensors",
96
+ "text_model.model.layers.12.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
97
+ "text_model.model.layers.12.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "text_model.model.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
99
+ "text_model.model.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
100
+ "text_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
101
+ "text_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
102
+ "text_model.model.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
103
+ "text_model.model.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
104
+ "text_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
105
+ "text_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "text_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
107
+ "text_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "text_model.model.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
109
+ "text_model.model.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
110
+ "text_model.model.layers.13.ffn.fc1.bias": "model-00001-of-00002.safetensors",
111
+ "text_model.model.layers.13.ffn.fc1.weight": "model-00001-of-00002.safetensors",
112
+ "text_model.model.layers.13.ffn.fc2.bias": "model-00001-of-00002.safetensors",
113
+ "text_model.model.layers.13.ffn.fc2.weight": "model-00001-of-00002.safetensors",
114
+ "text_model.model.layers.13.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
115
+ "text_model.model.layers.13.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "text_model.model.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
117
+ "text_model.model.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
118
+ "text_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
119
+ "text_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
120
+ "text_model.model.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
121
+ "text_model.model.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
122
+ "text_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
123
+ "text_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "text_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
125
+ "text_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
126
+ "text_model.model.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
127
+ "text_model.model.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
128
+ "text_model.model.layers.14.ffn.fc1.bias": "model-00001-of-00002.safetensors",
129
+ "text_model.model.layers.14.ffn.fc1.weight": "model-00001-of-00002.safetensors",
130
+ "text_model.model.layers.14.ffn.fc2.bias": "model-00001-of-00002.safetensors",
131
+ "text_model.model.layers.14.ffn.fc2.weight": "model-00001-of-00002.safetensors",
132
+ "text_model.model.layers.14.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
133
+ "text_model.model.layers.14.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "text_model.model.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
135
+ "text_model.model.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
136
+ "text_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
137
+ "text_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
138
+ "text_model.model.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
139
+ "text_model.model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
140
+ "text_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
141
+ "text_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "text_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
143
+ "text_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
144
+ "text_model.model.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
145
+ "text_model.model.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
146
+ "text_model.model.layers.15.ffn.fc1.bias": "model-00001-of-00002.safetensors",
147
+ "text_model.model.layers.15.ffn.fc1.weight": "model-00001-of-00002.safetensors",
148
+ "text_model.model.layers.15.ffn.fc2.bias": "model-00001-of-00002.safetensors",
149
+ "text_model.model.layers.15.ffn.fc2.weight": "model-00001-of-00002.safetensors",
150
+ "text_model.model.layers.15.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
151
+ "text_model.model.layers.15.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "text_model.model.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
153
+ "text_model.model.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
154
+ "text_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
155
+ "text_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
156
+ "text_model.model.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
157
+ "text_model.model.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
158
+ "text_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
159
+ "text_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "text_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
161
+ "text_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "text_model.model.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
163
+ "text_model.model.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
164
+ "text_model.model.layers.16.ffn.fc1.bias": "model-00001-of-00002.safetensors",
165
+ "text_model.model.layers.16.ffn.fc1.weight": "model-00001-of-00002.safetensors",
166
+ "text_model.model.layers.16.ffn.fc2.bias": "model-00001-of-00002.safetensors",
167
+ "text_model.model.layers.16.ffn.fc2.weight": "model-00001-of-00002.safetensors",
168
+ "text_model.model.layers.16.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
169
+ "text_model.model.layers.16.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "text_model.model.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
171
+ "text_model.model.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
172
+ "text_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
173
+ "text_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
174
+ "text_model.model.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
175
+ "text_model.model.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
176
+ "text_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
177
+ "text_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
178
+ "text_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
179
+ "text_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "text_model.model.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
181
+ "text_model.model.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
182
+ "text_model.model.layers.17.ffn.fc1.bias": "model-00001-of-00002.safetensors",
183
+ "text_model.model.layers.17.ffn.fc1.weight": "model-00001-of-00002.safetensors",
184
+ "text_model.model.layers.17.ffn.fc2.bias": "model-00001-of-00002.safetensors",
185
+ "text_model.model.layers.17.ffn.fc2.weight": "model-00001-of-00002.safetensors",
186
+ "text_model.model.layers.17.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
187
+ "text_model.model.layers.17.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "text_model.model.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
189
+ "text_model.model.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
190
+ "text_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
191
+ "text_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
192
+ "text_model.model.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
193
+ "text_model.model.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
194
+ "text_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
195
+ "text_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
196
+ "text_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
197
+ "text_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
198
+ "text_model.model.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
199
+ "text_model.model.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
200
+ "text_model.model.layers.18.ffn.fc1.bias": "model-00001-of-00002.safetensors",
201
+ "text_model.model.layers.18.ffn.fc1.weight": "model-00001-of-00002.safetensors",
202
+ "text_model.model.layers.18.ffn.fc2.bias": "model-00001-of-00002.safetensors",
203
+ "text_model.model.layers.18.ffn.fc2.weight": "model-00001-of-00002.safetensors",
204
+ "text_model.model.layers.18.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
205
+ "text_model.model.layers.18.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "text_model.model.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
207
+ "text_model.model.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
208
+ "text_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
209
+ "text_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
+ "text_model.model.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
211
+ "text_model.model.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
212
+ "text_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
213
+ "text_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "text_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
215
+ "text_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "text_model.model.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
217
+ "text_model.model.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
218
+ "text_model.model.layers.19.ffn.fc1.bias": "model-00001-of-00002.safetensors",
219
+ "text_model.model.layers.19.ffn.fc1.weight": "model-00001-of-00002.safetensors",
220
+ "text_model.model.layers.19.ffn.fc2.bias": "model-00001-of-00002.safetensors",
221
+ "text_model.model.layers.19.ffn.fc2.weight": "model-00001-of-00002.safetensors",
222
+ "text_model.model.layers.19.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
223
+ "text_model.model.layers.19.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "text_model.model.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
225
+ "text_model.model.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
226
+ "text_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
227
+ "text_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "text_model.model.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
229
+ "text_model.model.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
230
+ "text_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
231
+ "text_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "text_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
233
+ "text_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
234
+ "text_model.model.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
235
+ "text_model.model.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
236
+ "text_model.model.layers.2.ffn.fc1.bias": "model-00001-of-00002.safetensors",
237
+ "text_model.model.layers.2.ffn.fc1.weight": "model-00001-of-00002.safetensors",
238
+ "text_model.model.layers.2.ffn.fc2.bias": "model-00001-of-00002.safetensors",
239
+ "text_model.model.layers.2.ffn.fc2.weight": "model-00001-of-00002.safetensors",
240
+ "text_model.model.layers.2.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
241
+ "text_model.model.layers.2.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "text_model.model.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
243
+ "text_model.model.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
244
+ "text_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
245
+ "text_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
246
+ "text_model.model.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
247
+ "text_model.model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
248
+ "text_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
249
+ "text_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "text_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
251
+ "text_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
252
+ "text_model.model.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
253
+ "text_model.model.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
254
+ "text_model.model.layers.20.ffn.fc1.bias": "model-00001-of-00002.safetensors",
255
+ "text_model.model.layers.20.ffn.fc1.weight": "model-00001-of-00002.safetensors",
256
+ "text_model.model.layers.20.ffn.fc2.bias": "model-00001-of-00002.safetensors",
257
+ "text_model.model.layers.20.ffn.fc2.weight": "model-00001-of-00002.safetensors",
258
+ "text_model.model.layers.20.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
259
+ "text_model.model.layers.20.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
260
+ "text_model.model.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
261
+ "text_model.model.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
262
+ "text_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
263
+ "text_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
264
+ "text_model.model.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
265
+ "text_model.model.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
266
+ "text_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
267
+ "text_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "text_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
269
+ "text_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
270
+ "text_model.model.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
271
+ "text_model.model.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
272
+ "text_model.model.layers.21.ffn.fc1.bias": "model-00001-of-00002.safetensors",
273
+ "text_model.model.layers.21.ffn.fc1.weight": "model-00001-of-00002.safetensors",
274
+ "text_model.model.layers.21.ffn.fc2.bias": "model-00001-of-00002.safetensors",
275
+ "text_model.model.layers.21.ffn.fc2.weight": "model-00001-of-00002.safetensors",
276
+ "text_model.model.layers.21.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
277
+ "text_model.model.layers.21.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "text_model.model.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
279
+ "text_model.model.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
280
+ "text_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
281
+ "text_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
282
+ "text_model.model.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
283
+ "text_model.model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
284
+ "text_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
285
+ "text_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "text_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
287
+ "text_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
+ "text_model.model.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
289
+ "text_model.model.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
290
+ "text_model.model.layers.22.ffn.fc1.bias": "model-00001-of-00002.safetensors",
291
+ "text_model.model.layers.22.ffn.fc1.weight": "model-00001-of-00002.safetensors",
292
+ "text_model.model.layers.22.ffn.fc2.bias": "model-00001-of-00002.safetensors",
293
+ "text_model.model.layers.22.ffn.fc2.weight": "model-00001-of-00002.safetensors",
294
+ "text_model.model.layers.22.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
295
+ "text_model.model.layers.22.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
296
+ "text_model.model.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
297
+ "text_model.model.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
298
+ "text_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
299
+ "text_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
300
+ "text_model.model.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
301
+ "text_model.model.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
302
+ "text_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
303
+ "text_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
304
+ "text_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
305
+ "text_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
306
+ "text_model.model.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
307
+ "text_model.model.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
308
+ "text_model.model.layers.23.ffn.fc1.bias": "model-00001-of-00002.safetensors",
309
+ "text_model.model.layers.23.ffn.fc1.weight": "model-00001-of-00002.safetensors",
310
+ "text_model.model.layers.23.ffn.fc2.bias": "model-00001-of-00002.safetensors",
311
+ "text_model.model.layers.23.ffn.fc2.weight": "model-00001-of-00002.safetensors",
312
+ "text_model.model.layers.23.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
313
+ "text_model.model.layers.23.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "text_model.model.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
315
+ "text_model.model.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
316
+ "text_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
317
+ "text_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
318
+ "text_model.model.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
319
+ "text_model.model.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
320
+ "text_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
321
+ "text_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
322
+ "text_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
323
+ "text_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
324
+ "text_model.model.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
325
+ "text_model.model.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
326
+ "text_model.model.layers.3.ffn.fc1.bias": "model-00001-of-00002.safetensors",
327
+ "text_model.model.layers.3.ffn.fc1.weight": "model-00001-of-00002.safetensors",
328
+ "text_model.model.layers.3.ffn.fc2.bias": "model-00001-of-00002.safetensors",
329
+ "text_model.model.layers.3.ffn.fc2.weight": "model-00001-of-00002.safetensors",
330
+ "text_model.model.layers.3.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
331
+ "text_model.model.layers.3.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
332
+ "text_model.model.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
333
+ "text_model.model.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
334
+ "text_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
335
+ "text_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
336
+ "text_model.model.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
337
+ "text_model.model.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
338
+ "text_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
339
+ "text_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
340
+ "text_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
341
+ "text_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
342
+ "text_model.model.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
343
+ "text_model.model.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
344
+ "text_model.model.layers.4.ffn.fc1.bias": "model-00001-of-00002.safetensors",
345
+ "text_model.model.layers.4.ffn.fc1.weight": "model-00001-of-00002.safetensors",
346
+ "text_model.model.layers.4.ffn.fc2.bias": "model-00001-of-00002.safetensors",
347
+ "text_model.model.layers.4.ffn.fc2.weight": "model-00001-of-00002.safetensors",
348
+ "text_model.model.layers.4.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
349
+ "text_model.model.layers.4.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "text_model.model.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
351
+ "text_model.model.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
352
+ "text_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
353
+ "text_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
354
+ "text_model.model.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
355
+ "text_model.model.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
356
+ "text_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
357
+ "text_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
358
+ "text_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
359
+ "text_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "text_model.model.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
361
+ "text_model.model.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
362
+ "text_model.model.layers.5.ffn.fc1.bias": "model-00001-of-00002.safetensors",
363
+ "text_model.model.layers.5.ffn.fc1.weight": "model-00001-of-00002.safetensors",
364
+ "text_model.model.layers.5.ffn.fc2.bias": "model-00001-of-00002.safetensors",
365
+ "text_model.model.layers.5.ffn.fc2.weight": "model-00001-of-00002.safetensors",
366
+ "text_model.model.layers.5.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
367
+ "text_model.model.layers.5.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
368
+ "text_model.model.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
369
+ "text_model.model.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
370
+ "text_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
371
+ "text_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
372
+ "text_model.model.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
373
+ "text_model.model.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
374
+ "text_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
375
+ "text_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
376
+ "text_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
377
+ "text_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
378
+ "text_model.model.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
379
+ "text_model.model.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
380
+ "text_model.model.layers.6.ffn.fc1.bias": "model-00001-of-00002.safetensors",
381
+ "text_model.model.layers.6.ffn.fc1.weight": "model-00001-of-00002.safetensors",
382
+ "text_model.model.layers.6.ffn.fc2.bias": "model-00001-of-00002.safetensors",
383
+ "text_model.model.layers.6.ffn.fc2.weight": "model-00001-of-00002.safetensors",
384
+ "text_model.model.layers.6.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
385
+ "text_model.model.layers.6.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "text_model.model.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
387
+ "text_model.model.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
388
+ "text_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
389
+ "text_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
390
+ "text_model.model.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
391
+ "text_model.model.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
392
+ "text_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
393
+ "text_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
394
+ "text_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
395
+ "text_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
396
+ "text_model.model.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
397
+ "text_model.model.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
398
+ "text_model.model.layers.7.ffn.fc1.bias": "model-00001-of-00002.safetensors",
399
+ "text_model.model.layers.7.ffn.fc1.weight": "model-00001-of-00002.safetensors",
400
+ "text_model.model.layers.7.ffn.fc2.bias": "model-00001-of-00002.safetensors",
401
+ "text_model.model.layers.7.ffn.fc2.weight": "model-00001-of-00002.safetensors",
402
+ "text_model.model.layers.7.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
403
+ "text_model.model.layers.7.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "text_model.model.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
405
+ "text_model.model.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
406
+ "text_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
407
+ "text_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
408
+ "text_model.model.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
409
+ "text_model.model.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
410
+ "text_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
411
+ "text_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
412
+ "text_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
413
+ "text_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
414
+ "text_model.model.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
415
+ "text_model.model.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
416
+ "text_model.model.layers.8.ffn.fc1.bias": "model-00001-of-00002.safetensors",
417
+ "text_model.model.layers.8.ffn.fc1.weight": "model-00001-of-00002.safetensors",
418
+ "text_model.model.layers.8.ffn.fc2.bias": "model-00001-of-00002.safetensors",
419
+ "text_model.model.layers.8.ffn.fc2.weight": "model-00001-of-00002.safetensors",
420
+ "text_model.model.layers.8.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
421
+ "text_model.model.layers.8.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
422
+ "text_model.model.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
423
+ "text_model.model.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
424
+ "text_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
425
+ "text_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
426
+ "text_model.model.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
427
+ "text_model.model.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
428
+ "text_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
429
+ "text_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
430
+ "text_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
431
+ "text_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
432
+ "text_model.model.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
433
+ "text_model.model.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
434
+ "text_model.model.layers.9.ffn.fc1.bias": "model-00001-of-00002.safetensors",
435
+ "text_model.model.layers.9.ffn.fc1.weight": "model-00001-of-00002.safetensors",
436
+ "text_model.model.layers.9.ffn.fc2.bias": "model-00001-of-00002.safetensors",
437
+ "text_model.model.layers.9.ffn.fc2.weight": "model-00001-of-00002.safetensors",
438
+ "text_model.model.layers.9.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
439
+ "text_model.model.layers.9.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
440
+ "text_model.model.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
441
+ "text_model.model.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
442
+ "text_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
443
+ "text_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
444
+ "text_model.model.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
445
+ "text_model.model.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
446
+ "text_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
447
+ "text_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
448
+ "text_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
449
+ "text_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
+ "text_model.model.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
451
+ "text_model.model.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
452
+ "text_model.model.segment_emb.weight": "model-00001-of-00002.safetensors",
453
+ "vision_model.embeddings.column_embedder.weight": "model-00001-of-00002.safetensors",
454
+ "vision_model.embeddings.patch_projection.bias": "model-00001-of-00002.safetensors",
455
+ "vision_model.embeddings.patch_projection.weight": "model-00001-of-00002.safetensors",
456
+ "vision_model.embeddings.row_embedder.weight": "model-00001-of-00002.safetensors",
457
+ "vision_model.encoder.layer.0.attention.key.weight": "model-00001-of-00002.safetensors",
458
+ "vision_model.encoder.layer.0.attention.output.weight": "model-00001-of-00002.safetensors",
459
+ "vision_model.encoder.layer.0.attention.query.weight": "model-00001-of-00002.safetensors",
460
+ "vision_model.encoder.layer.0.attention.value.weight": "model-00001-of-00002.safetensors",
461
+ "vision_model.encoder.layer.0.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
462
+ "vision_model.encoder.layer.0.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
463
+ "vision_model.encoder.layer.0.mlp.wo.weight": "model-00001-of-00002.safetensors",
464
+ "vision_model.encoder.layer.0.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
465
+ "vision_model.encoder.layer.0.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
466
+ "vision_model.encoder.layer.1.attention.key.weight": "model-00001-of-00002.safetensors",
467
+ "vision_model.encoder.layer.1.attention.output.weight": "model-00001-of-00002.safetensors",
468
+ "vision_model.encoder.layer.1.attention.query.weight": "model-00001-of-00002.safetensors",
469
+ "vision_model.encoder.layer.1.attention.value.weight": "model-00001-of-00002.safetensors",
470
+ "vision_model.encoder.layer.1.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
471
+ "vision_model.encoder.layer.1.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
472
+ "vision_model.encoder.layer.1.mlp.wo.weight": "model-00001-of-00002.safetensors",
473
+ "vision_model.encoder.layer.1.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
474
+ "vision_model.encoder.layer.1.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
475
+ "vision_model.encoder.layer.10.attention.key.weight": "model-00001-of-00002.safetensors",
476
+ "vision_model.encoder.layer.10.attention.output.weight": "model-00001-of-00002.safetensors",
477
+ "vision_model.encoder.layer.10.attention.query.weight": "model-00001-of-00002.safetensors",
478
+ "vision_model.encoder.layer.10.attention.value.weight": "model-00001-of-00002.safetensors",
479
+ "vision_model.encoder.layer.10.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
480
+ "vision_model.encoder.layer.10.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
481
+ "vision_model.encoder.layer.10.mlp.wo.weight": "model-00001-of-00002.safetensors",
482
+ "vision_model.encoder.layer.10.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
483
+ "vision_model.encoder.layer.10.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
484
+ "vision_model.encoder.layer.11.attention.key.weight": "model-00001-of-00002.safetensors",
485
+ "vision_model.encoder.layer.11.attention.output.weight": "model-00001-of-00002.safetensors",
486
+ "vision_model.encoder.layer.11.attention.query.weight": "model-00001-of-00002.safetensors",
487
+ "vision_model.encoder.layer.11.attention.value.weight": "model-00001-of-00002.safetensors",
488
+ "vision_model.encoder.layer.11.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
489
+ "vision_model.encoder.layer.11.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
490
+ "vision_model.encoder.layer.11.mlp.wo.weight": "model-00001-of-00002.safetensors",
491
+ "vision_model.encoder.layer.11.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
492
+ "vision_model.encoder.layer.11.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
493
+ "vision_model.encoder.layer.12.attention.key.weight": "model-00001-of-00002.safetensors",
494
+ "vision_model.encoder.layer.12.attention.output.weight": "model-00001-of-00002.safetensors",
495
+ "vision_model.encoder.layer.12.attention.query.weight": "model-00001-of-00002.safetensors",
496
+ "vision_model.encoder.layer.12.attention.value.weight": "model-00001-of-00002.safetensors",
497
+ "vision_model.encoder.layer.12.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
498
+ "vision_model.encoder.layer.12.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
499
+ "vision_model.encoder.layer.12.mlp.wo.weight": "model-00001-of-00002.safetensors",
500
+ "vision_model.encoder.layer.12.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
501
+ "vision_model.encoder.layer.12.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
502
+ "vision_model.encoder.layer.13.attention.key.weight": "model-00001-of-00002.safetensors",
503
+ "vision_model.encoder.layer.13.attention.output.weight": "model-00001-of-00002.safetensors",
504
+ "vision_model.encoder.layer.13.attention.query.weight": "model-00001-of-00002.safetensors",
505
+ "vision_model.encoder.layer.13.attention.value.weight": "model-00001-of-00002.safetensors",
506
+ "vision_model.encoder.layer.13.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
507
+ "vision_model.encoder.layer.13.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
508
+ "vision_model.encoder.layer.13.mlp.wo.weight": "model-00001-of-00002.safetensors",
509
+ "vision_model.encoder.layer.13.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
510
+ "vision_model.encoder.layer.13.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
511
+ "vision_model.encoder.layer.14.attention.key.weight": "model-00002-of-00002.safetensors",
512
+ "vision_model.encoder.layer.14.attention.output.weight": "model-00002-of-00002.safetensors",
513
+ "vision_model.encoder.layer.14.attention.query.weight": "model-00002-of-00002.safetensors",
514
+ "vision_model.encoder.layer.14.attention.value.weight": "model-00002-of-00002.safetensors",
515
+ "vision_model.encoder.layer.14.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
516
+ "vision_model.encoder.layer.14.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
517
+ "vision_model.encoder.layer.14.mlp.wo.weight": "model-00002-of-00002.safetensors",
518
+ "vision_model.encoder.layer.14.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
519
+ "vision_model.encoder.layer.14.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
520
+ "vision_model.encoder.layer.15.attention.key.weight": "model-00002-of-00002.safetensors",
521
+ "vision_model.encoder.layer.15.attention.output.weight": "model-00002-of-00002.safetensors",
522
+ "vision_model.encoder.layer.15.attention.query.weight": "model-00002-of-00002.safetensors",
523
+ "vision_model.encoder.layer.15.attention.value.weight": "model-00002-of-00002.safetensors",
524
+ "vision_model.encoder.layer.15.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
525
+ "vision_model.encoder.layer.15.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
526
+ "vision_model.encoder.layer.15.mlp.wo.weight": "model-00002-of-00002.safetensors",
527
+ "vision_model.encoder.layer.15.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
528
+ "vision_model.encoder.layer.15.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
529
+ "vision_model.encoder.layer.16.attention.key.weight": "model-00002-of-00002.safetensors",
530
+ "vision_model.encoder.layer.16.attention.output.weight": "model-00002-of-00002.safetensors",
531
+ "vision_model.encoder.layer.16.attention.query.weight": "model-00002-of-00002.safetensors",
532
+ "vision_model.encoder.layer.16.attention.value.weight": "model-00002-of-00002.safetensors",
533
+ "vision_model.encoder.layer.16.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
534
+ "vision_model.encoder.layer.16.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
535
+ "vision_model.encoder.layer.16.mlp.wo.weight": "model-00002-of-00002.safetensors",
536
+ "vision_model.encoder.layer.16.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
537
+ "vision_model.encoder.layer.16.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
538
+ "vision_model.encoder.layer.17.attention.key.weight": "model-00002-of-00002.safetensors",
539
+ "vision_model.encoder.layer.17.attention.output.weight": "model-00002-of-00002.safetensors",
540
+ "vision_model.encoder.layer.17.attention.query.weight": "model-00002-of-00002.safetensors",
541
+ "vision_model.encoder.layer.17.attention.value.weight": "model-00002-of-00002.safetensors",
542
+ "vision_model.encoder.layer.17.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
543
+ "vision_model.encoder.layer.17.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
544
+ "vision_model.encoder.layer.17.mlp.wo.weight": "model-00002-of-00002.safetensors",
545
+ "vision_model.encoder.layer.17.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
546
+ "vision_model.encoder.layer.17.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
547
+ "vision_model.encoder.layer.2.attention.key.weight": "model-00001-of-00002.safetensors",
548
+ "vision_model.encoder.layer.2.attention.output.weight": "model-00001-of-00002.safetensors",
549
+ "vision_model.encoder.layer.2.attention.query.weight": "model-00001-of-00002.safetensors",
550
+ "vision_model.encoder.layer.2.attention.value.weight": "model-00001-of-00002.safetensors",
551
+ "vision_model.encoder.layer.2.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
552
+ "vision_model.encoder.layer.2.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
553
+ "vision_model.encoder.layer.2.mlp.wo.weight": "model-00001-of-00002.safetensors",
554
+ "vision_model.encoder.layer.2.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
555
+ "vision_model.encoder.layer.2.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
556
+ "vision_model.encoder.layer.3.attention.key.weight": "model-00001-of-00002.safetensors",
557
+ "vision_model.encoder.layer.3.attention.output.weight": "model-00001-of-00002.safetensors",
558
+ "vision_model.encoder.layer.3.attention.query.weight": "model-00001-of-00002.safetensors",
559
+ "vision_model.encoder.layer.3.attention.value.weight": "model-00001-of-00002.safetensors",
560
+ "vision_model.encoder.layer.3.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
561
+ "vision_model.encoder.layer.3.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
562
+ "vision_model.encoder.layer.3.mlp.wo.weight": "model-00001-of-00002.safetensors",
563
+ "vision_model.encoder.layer.3.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
564
+ "vision_model.encoder.layer.3.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
565
+ "vision_model.encoder.layer.4.attention.key.weight": "model-00001-of-00002.safetensors",
566
+ "vision_model.encoder.layer.4.attention.output.weight": "model-00001-of-00002.safetensors",
567
+ "vision_model.encoder.layer.4.attention.query.weight": "model-00001-of-00002.safetensors",
568
+ "vision_model.encoder.layer.4.attention.value.weight": "model-00001-of-00002.safetensors",
569
+ "vision_model.encoder.layer.4.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
570
+ "vision_model.encoder.layer.4.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
571
+ "vision_model.encoder.layer.4.mlp.wo.weight": "model-00001-of-00002.safetensors",
572
+ "vision_model.encoder.layer.4.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
573
+ "vision_model.encoder.layer.4.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
574
+ "vision_model.encoder.layer.5.attention.key.weight": "model-00001-of-00002.safetensors",
575
+ "vision_model.encoder.layer.5.attention.output.weight": "model-00001-of-00002.safetensors",
576
+ "vision_model.encoder.layer.5.attention.query.weight": "model-00001-of-00002.safetensors",
577
+ "vision_model.encoder.layer.5.attention.value.weight": "model-00001-of-00002.safetensors",
578
+ "vision_model.encoder.layer.5.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
579
+ "vision_model.encoder.layer.5.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
580
+ "vision_model.encoder.layer.5.mlp.wo.weight": "model-00001-of-00002.safetensors",
581
+ "vision_model.encoder.layer.5.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
582
+ "vision_model.encoder.layer.5.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
583
+ "vision_model.encoder.layer.6.attention.key.weight": "model-00001-of-00002.safetensors",
584
+ "vision_model.encoder.layer.6.attention.output.weight": "model-00001-of-00002.safetensors",
585
+ "vision_model.encoder.layer.6.attention.query.weight": "model-00001-of-00002.safetensors",
586
+ "vision_model.encoder.layer.6.attention.value.weight": "model-00001-of-00002.safetensors",
587
+ "vision_model.encoder.layer.6.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
588
+ "vision_model.encoder.layer.6.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
589
+ "vision_model.encoder.layer.6.mlp.wo.weight": "model-00001-of-00002.safetensors",
590
+ "vision_model.encoder.layer.6.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
591
+ "vision_model.encoder.layer.6.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
592
+ "vision_model.encoder.layer.7.attention.key.weight": "model-00001-of-00002.safetensors",
593
+ "vision_model.encoder.layer.7.attention.output.weight": "model-00001-of-00002.safetensors",
594
+ "vision_model.encoder.layer.7.attention.query.weight": "model-00001-of-00002.safetensors",
595
+ "vision_model.encoder.layer.7.attention.value.weight": "model-00001-of-00002.safetensors",
596
+ "vision_model.encoder.layer.7.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
597
+ "vision_model.encoder.layer.7.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
598
+ "vision_model.encoder.layer.7.mlp.wo.weight": "model-00001-of-00002.safetensors",
599
+ "vision_model.encoder.layer.7.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
600
+ "vision_model.encoder.layer.7.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
601
+ "vision_model.encoder.layer.8.attention.key.weight": "model-00001-of-00002.safetensors",
602
+ "vision_model.encoder.layer.8.attention.output.weight": "model-00001-of-00002.safetensors",
603
+ "vision_model.encoder.layer.8.attention.query.weight": "model-00001-of-00002.safetensors",
604
+ "vision_model.encoder.layer.8.attention.value.weight": "model-00001-of-00002.safetensors",
605
+ "vision_model.encoder.layer.8.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
606
+ "vision_model.encoder.layer.8.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
607
+ "vision_model.encoder.layer.8.mlp.wo.weight": "model-00001-of-00002.safetensors",
608
+ "vision_model.encoder.layer.8.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
609
+ "vision_model.encoder.layer.8.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
610
+ "vision_model.encoder.layer.9.attention.key.weight": "model-00001-of-00002.safetensors",
611
+ "vision_model.encoder.layer.9.attention.output.weight": "model-00001-of-00002.safetensors",
612
+ "vision_model.encoder.layer.9.attention.query.weight": "model-00001-of-00002.safetensors",
613
+ "vision_model.encoder.layer.9.attention.value.weight": "model-00001-of-00002.safetensors",
614
+ "vision_model.encoder.layer.9.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
615
+ "vision_model.encoder.layer.9.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
616
+ "vision_model.encoder.layer.9.mlp.wo.weight": "model-00001-of-00002.safetensors",
617
+ "vision_model.encoder.layer.9.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
618
+ "vision_model.encoder.layer.9.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
619
+ "vision_model.layernorm.weight": "model-00002-of-00002.safetensors"
620
+ }
621
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "image_processor_type": "Kosmos2_5ImageProcessor",
3
+ "processor_class": "Kosmos2_5Processor"
4
+ }
5
+
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 4096,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "PreTrainedTokenizerFast",
9
+ "unk_token": "<unk>"
10
+ }