Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ license: mit
 
 <div>
 <p style="margin-top: 0;margin-bottom: 0;">
-    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+    <em>This DeepSeek-OCR upload was edited to enable inference & fine-tuning on the latest transformers (no accuracy change). <a href="https://docs.unsloth.ai/new/deepseek-ocr-run-and-fine-tune#fine-tuning-deepseek-ocr">Read more</a></em>
   </p>
   <div style="display: flex; gap: 5px; align-items: center; ">
     <a href="https://github.com/unslothai/unsloth/">
@@ -32,6 +32,7 @@ license: mit
 <h1 style="margin-top: 0rem;">✨ Read our DeepSeek-OCR Guide <a href="https://docs.unsloth.ai/new/deepseek-ocr">here</a>!</h1>
 </div>
 
+- Thank you to [Prithiv's](https://huggingface.co/prithivMLmods/DeepSeek-OCR-Latest-BF16.I64) model modifcations that enables DeepSeek-OCR fine-tuning.
 - Fine-tune DeepSeek-OCR for free using our [Google Colab notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Deepseek_OCR_(3B).ipynb)
 - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
 

model-00001-of-000001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1169e7cdc28ff2fb6186556acb2175db148ad26a62097df4c45a17e523180d3f
+size 6672547120

modeling_deepseekocr.py

@@ -370,7 +370,7 @@ def decoder_layer_init(self, config: DeepseekV2Config, layer_idx: int):
 DeepseekV2DecoderLayer.__init__ = decoder_layer_init
 
 class DeepseekOCRConfig(DeepseekV2Config):
-    model_type = "DeepseekOCR"
+    model_type = "deepseek_ocr"
 
 class DeepseekOCRModel(DeepseekV2Model):
     config_class = DeepseekOCRConfig
@@ -1040,4 +1040,4 @@ class DeepseekOCRForCausalLM(DeepseekV2ForCausalLM):
                 plt.savefig(f'{output_path}/geo.jpg')
                 plt.close()
 
-            result.save(f"{output_path}/result_with_boxes.jpg")
+            result.save(f"{output_path}/result_with_boxes.jpg")