update readme

.gitattributes

@@ -33,9 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-receipt_00008.png filter=lfs diff=lfs merge=lfs -text
-.png filter=lfs diff=lfs merge=lfs -text
-*.md filter=lfs diff=lfs merge=lfs -text
-*.py filter=lfs diff=lfs merge=lfs -text
-*.json filter=lfs diff=lfs merge=lfs -text
 *.png filter=lfs diff=lfs merge=lfs -text
+

README.md

@@ -1,3 +1,81 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4d1c384c76fca9be88593a39f73619c7594ac476eb1fb278be62f702d1d6ef1c
-size 4782
+---
+language: en
+license: mit
+---
+# Kosmos-2.5 (Testing)
+
+[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://github.com/microsoft/unilm/tree/master/kosmos-2.5)
+
+## Model description
+
+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.
+
+[Kosmos-2.5: A Multimodal Literate Model](https://arxiv.org/abs/2309.11419)
+
+## NOTE
+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.
+
+## Download transformers：
+```bash
+pip install git+https://github.com/tic-top/transformers.git
+```
+This repo will be soon merged to official Transformers.
+
+## Usage
+### OCR
+Run with [ocr.py](ocr.py).
+```text
+55,595,71,595,71,629,55,629,1
+82,595,481,595,481,635,82,635,[REG] BLACK SAKURA
+716,590,841,590,841,629,716,629,45,455
+55,637,71,637,71,672,55,672,1
+82,637,486,637,486,675,82,675,COOKIE DOH SAUCES
+818,632,843,632,843,668,818,668,0
+51,683,71,683,71,719,51,719,1
+82,683,371,683,371,719,82,719,NATA DE COCO
+820,677,845,677,845,713,820,713,0
+32,770,851,770,851,811,32,811,Sub Total 45,455
+28,811,853,811,853,858,28,858,PB1 (10%) 4,545
+28,857,855,857,855,905,28,905,Rounding 0
+24,905,858,905,858,956,24,956,Total 50,000
+17,1096,868,1096,868,1150,17,1150,Card Payment 50,000
+```
+![output](output.png)
+### Markdown
+Run with [md.py](md.py).
+
+```text
+- **1 \[REG\] BLACK SAKURA** 45,455
+- **1 COOKIE DOH SAUCES** 0
+- **1 NATA DE COCO** 0
+- **Sub Total** 45,455
+- **PB1 (10%)** 4,545
+- **Rounding** 0
+- **Total** **50,000**
+
+Card Payment 50,000
+```
+
+
+
+
+## Citation
+
+If you find Kosmos-2.5 useful in your research, please cite the following paper:
+
+```
+@article{lv2023kosmos,
+  title={Kosmos-2.5: A multimodal literate model},
+  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},
+  journal={arXiv preprint arXiv:2309.11419},
+  year={2023}
+}
+```
+
+## License
+The content of this project itself is licensed under the [MIT](https://github.com/microsoft/unilm/blob/master/kosmos-2.5/LICENSE)
+
+[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)
+
+
+

config.json

@@ -1,3 +1,151 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:42e69220468261c2da40171ffbbf33ba1991e101ac7f67709cae1b1b8e6ad991
-size 4033
+{
+  "architectures": [
+    "Kosmos2_5ForConditionalGeneration"
+  ],
+  "latent_query_num": 2048,
+  "model_type": "kosmos-2.5",
+  "text_config": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "attention_heads": 16,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dropout": 0,
+    "early_stopping": false,
+    "embed_dim": 1536,
+    "pad_token_id": 1,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 6144,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.0,
+    "layers": 24,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "kosmos_2_5_text_model",
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torch_dtype": null,
+    "torchscript": false,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 108481
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 3968,
+    "d_kv": 64,
+    "decoder_start_token_id": null,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1536,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 1e-10,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 4096,
+    "min_length": 0,
+    "model_type": "kosmos_2_5_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 24,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 18,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_embed_hidden_size": 768,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "seq_len": 4096,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

generation_config.json

@@ -1,3 +1,9 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ff1351b6a1bc18f890c14bb6f08bdb7db7b056fd7df44ab4cc90d9f832d0091
-size 178
+{
+  "_from_model_config": false,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.0.dev0",
+  "num_beam" : 1,
+  "do_sample": false
+}

md.py

@@ -0,0 +1,32 @@
+import re
+import torch
+import requests
+from PIL import Image, ImageDraw
+from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
+
+repo = "microsoft/kosmos-2.5" # 
+repo = "kirp/kosmos2_5"
+device = "cuda:0"
+dtype = torch.bfloat16
+model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
+processor = AutoProcessor.from_pretrained(repo)
+
+url = "https://huggingface.co/kirp/kosmos2_5/resolve/main/receipt_00008.png"
+image = Image.open(requests.get(url, stream=True).raw)
+prompt = "<md>"
+inputs = processor(text=prompt, images=image, return_tensors="pt")
+
+height, width = inputs.pop("height"), inputs.pop("width")
+raw_width, raw_height = image.size
+scale_height = raw_height / height
+scale_width = raw_width / width
+
+inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
+inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+)
+
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+print(generated_text[0])

model.safetensors.index.json

@@ -1,3 +1,621 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a1efccef236dea0c422e37d1584fa27b28c3dea5a09a98e2d6ef53c83a4830c
-size 56481
+{
+  "metadata": {
+    "total_size": 5498585088
+  },
+  "weight_map": {
+    "image_to_text_projection.dense.bias": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.dense.weight": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.latent_query": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "image_to_text_projection.x_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.ffn.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.ffn.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.ffn.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.ffn.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "text_model.model.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "text_model.model.segment_emb.weight": "model-00001-of-00002.safetensors",
+    "vision_model.embeddings.column_embedder.weight": "model-00001-of-00002.safetensors",
+    "vision_model.embeddings.patch_projection.bias": "model-00001-of-00002.safetensors",
+    "vision_model.embeddings.patch_projection.weight": "model-00001-of-00002.safetensors",
+    "vision_model.embeddings.row_embedder.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.0.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.1.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.10.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.11.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.12.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.13.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.14.attention.key.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.attention.output.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.attention.query.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.attention.value.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.mlp.wo.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.14.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.attention.key.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.attention.output.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.attention.query.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.attention.value.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.mlp.wo.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.15.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.attention.key.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.attention.output.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.attention.query.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.attention.value.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.mlp.wo.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.16.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.attention.key.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.attention.output.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.attention.query.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.attention.value.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.mlp.wo.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.17.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_model.encoder.layer.2.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.2.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.3.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.4.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.5.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.6.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.7.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.8.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.attention.key.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.attention.output.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.attention.query.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.attention.value.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.mlp.wo.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.encoder.layer.9.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_model.layernorm.weight": "model-00002-of-00002.safetensors"
+  }
+}

ocr.py

@@ -0,0 +1,68 @@
+import re
+import torch
+import requests
+from PIL import Image, ImageDraw
+from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
+
+
+repo = "microsoft/kosmos-2.5" # 
+repo = "kirp/kosmos2_5"
+device = "cuda:0"
+dtype = torch.bfloat16
+model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
+processor = AutoProcessor.from_pretrained(repo)
+
+url = "https://huggingface.co/kirp/kosmos2_5/resolve/main/receipt_00008.png"
+image = Image.open(requests.get(url, stream=True).raw)
+prompt = "<ocr>"
+inputs = processor(text=prompt, images=image, return_tensors="pt")
+# batch input
+# inputs = processor(text=[prompt, prompt], images=[image,image], return_tensors="pt")
+
+height, width = inputs.pop("height"), inputs.pop("width")
+raw_width, raw_height = image.size
+scale_height = raw_height / height
+scale_width = raw_width / width
+
+inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
+inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+)
+
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+def post_process(y, scale_height, scale_width):
+    y = y.replace(prompt, "")
+    if "<md>" in prompt:
+        return y
+    pattern = r"<bbox><x_\d+><y_\d+><x_\d+><y_\d+></bbox>"
+    bboxs_raw = re.findall(pattern, y)
+    lines = re.split(pattern, y)[1:]
+    bboxs = [re.findall(r"\d+", i) for i in bboxs_raw]
+    bboxs = [[int(j) for j in i] for i in bboxs]
+    info = ""
+    for i in range(len(lines)):
+        box = bboxs[i]
+        x0, y0, x1, y1 = box
+        if not (x0 >= x1 or y0 >= y1):
+            x0 = int(x0 * scale_width)
+            y0 = int(y0 * scale_height)
+            x1 = int(x1 * scale_width)
+            y1 = int(y1 * scale_height)
+            info += f"{x0},{y0},{x1},{y0},{x1},{y1},{x0},{y1},{lines[i]}"
+    return info
+
+output_text = post_process(generated_text[0], scale_height, scale_width)
+print(output_text)
+
+draw = ImageDraw.Draw(image)
+lines = output_text.split("\n")
+for line in lines:
+    # draw the bounding box
+    line = list(line.split(","))
+    if len(line) < 8:
+        continue
+    line = list(map(int, line[:8]))
+    draw.polygon(line, outline="red")
+image.save("output.png")

preprocessor_config.json

@@ -1,3 +1,5 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef824d8f3f414c73cf63f2005deeaabee79fa91ad9b882b35d653fb296903116
-size 107
+{
+    "image_processor_type": "Kosmos2_5ImageProcessor",
+    "processor_class": "Kosmos2_5Processor"
+  }
+  

tokenizer_config.json

@@ -1,3 +1,10 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8c959ced5608848b4eef52b9df43cb26878e0c33758009ea8587d233ba14b16
-size 242
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}