uploaded readme

README.md

@@ -0,0 +1,32 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+llava-phi3-3.8b-lora - bnb 8bits
+- Model creator: https://huggingface.co/praysimanjuntak/
+- Original model: https://huggingface.co/praysimanjuntak/llava-phi3-3.8b-lora/
+
+
+
+
+Original model description:
+---
+base_model: microsoft/Phi-3-mini-128k-instruct
+inference: false
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+A [LLaVA (Large Language and Vision Assistant)](https://github.com/haotian-liu/LLaVA) version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
+
+
+## Model Details
+
+Trained with this dataset of [liuhaotian/LLaVA-Instruct-150K](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K). This model has a around 4.1B parameters, where the 3.8B came from the base model.
+