Update README.md

README.md

@@ -7,15 +7,22 @@ tags:
 - transformers
 - unsloth
 - mistral
+- trl
+- sft
 - gguf
 base_model: unsloth/mistral-7b-v0.2-bnb-4bit
+datasets:
+- visheratin/realworldqa
 ---
+# Mistral-RealworldQA-7b SFT GGUF
 
-# Uploaded model
+<img src="https://i.imgur.com/Pf53ms5.jpeg" width="400"/>
+
+Original fp16 weights [here](https://huggingface.co/InferenceIllusionist/Mistral-RealworldQA-7b-SFT).
+
+An experiment with the goal of reducing halucinations in [VQA](https://huggingface.co/tasks/visual-question-answering).
+First in of a series of projects centering around fine-tuning for image captioning.
 
-- **Developed by:** InferenceIllusionist
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/mistral-7b-v0.2-bnb-4bit
 
 This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.