Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+base_model: deepseek-ai/DeepSeek-OCR
+library_name: peft
+tags:
+- lora
+- ocr
+- deepseek
+- unsloth
+pipeline_tag: image-text-to-text
+license: mit
+---
+
+# LoRA Adapter for DeepSeek-OCR (Vietnamese Bills)
+
+This repository contains LoRA fine-tuned weights for the model
+**deepseek-ai/DeepSeek-OCR**, specialized for OCR tasks.
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "deepseek-ai/DeepSeek-OCR"
+lora = "giayphuyen/lora_model"
+
+tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
+model = AutoModel.from_pretrained(base, trust_remote_code=True).cuda()
+
+model = PeftModel.from_pretrained(model, lora)
+model = model.eval().to(torch.bfloat16)
+
+prompt = "<image>\nExtract the text."
+image = "your_image.jpg"
+
+res = model.infer(
+    tokenizer,
+    prompt=prompt,
+    image_file=image,
+    output_path=".",
+)
+print(res)

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "DeepseekOCRForCausalLM",
+    "parent_library": "transformers_modules.deepseek_ocr.modeling_deepseekocr",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "./deepseek_ocr",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433c792704bc2ec04011e6c221d06f6a8976d6b57e2b726ed7859ec74dfa2a08
+size 310662536

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}