Update README.md

README.md

@@ -12,9 +12,12 @@ pipeline_tag: visual-question-answering
 
 # paligemma-3b-ft-docvqa-896-lora
 
-paligemma-3b-ft-docvqa-896-lora is a Vision-Language Model (VLM) based on [google/paligemma-3b-ft-docvqa-896](https://huggingface.co/google/paligemma-3b-ft-docvqa-896/edit/main/README.md) model
-and trained in original LLaVA setup using LORA. This model is primarily adapted to work with French, but still capable to work with English.
 
+paligemma-3b-ft-docvqa-896-lora is a fine-tuned version of the [google/paligemma-3b-ft-docvqa-896](https://huggingface.co/google/paligemma-3b-ft-docvqa-896/edit/main/README.md) model, specifically trained on the [doc-vqa](https://huggingface.co/datasets/cmarkea/doc-vqa) dataset published by cmarkea. Optimized using the LoRA (Low-Rank Adaptation) method, this model was designed to enhance performance while reducing the complexity of fine-tuning.
+
+During training, particular attention was given to linguistic balance, with a focus on French. The model was exposed to a predominantly French context, with a 70% likelihood of interacting with French questions/answers for a given image. It operates exclusively in bfloat16 precision, optimizing computational resources.
+
+Thanks to its multilingual specialization and emphasis on French, this model excels in francophone environments, while also performing well in English. It is especially suited for tasks that require the analysis and understanding of complex documents, such as extracting information from forms, invoices, reports, and other text-based documents in a visual question-answering context.
 
 ## Model Details
 
@@ -49,7 +52,7 @@ image = Image.open(requests.get(url, stream=True).raw)
 
 model = PaliGemmaForConditionalGeneration.from_pretrained(
     model_id,
-    torch_dtype=dtype,
+    torch_dtype=torch.bfloat16,
     device_map=device,
 ).eval()
 
@@ -67,10 +70,6 @@ with torch.inference_mode():
     print(decoded)
 ```
 
-## Training Details
-
-[More Information Needed]
-
 
 ### Results