Update README.md

README.md

@@ -13,17 +13,18 @@ tags: []
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+Initially, Pixprompt is the first open-source small LLM, Pixprompt combines a CLIP vision encoder and GPT-2 (125M) decoder, with optional LoRA adapters for efficient fine-tuning. It was originally trained to support image + prompt → text, and now fine-tuned on a curated set of financial data and news headlines fetched dynamically from the web.
+
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
 - **Developed by:** [Sree bhargavi balija]
 - **Funded by [optional]:** [self]
 - **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Model type:** [Multimodal Causal Language Model (CLIP + GPT2)]
+- **Language(s) (NLP):** [English]
+- **License:** [MIT]
+- **Finetuned from model [optional]:** [bhargavi909/Pixprompt]
 
 ### Model Sources [optional]
 
@@ -69,7 +70,17 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+from peft import PeftModel
+
+base = GPT2LMHeadModel.from_pretrained("bhargavi909/Pixprompt")
+model = PeftModel.from_pretrained(base, "./finetuned-financial-pixprompt")
+tokenizer = GPT2Tokenizer.from_pretrained("bhargavi909/Pixprompt")
+
+prompt = "The chart shows the impact of inflation"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 [More Information Needed]
 
@@ -170,7 +181,12 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Citation [optional]
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+@misc{pixprompt2024,
+  author = {Sree Bhargavi Balija},
+  title = {Pixprompt: A Multimodal GPT Model for Financial Text Generation},
+  year = {2024},
+  url = {https://huggingface.co/bhargavi909/Pixprompt},
+}
 
 **BibTeX:**