Update README.md

README.md

@@ -1,3 +1,42 @@
----
-license: mit
----
+---
+license: mit
+---
+# cvx-coder
+
+[Paper](https://github.com/jackfsuia/BertChunker/blob/main/main.pdf) | [Github](https://github.com/jackfsuia/BertChunker)
+
+## Introduction
+
+cvx-coder is a phi-3 model finetuned on a dataset of [CVX](https://cvxr.com/cvx) docs, codes, and forum conversations. Its aimed to improve the CVX code ability and QA ability of LLMs.
+
+## Quickstart
+Run the following:
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+m_path="/data/goodmodel"
+model = AutoModelForCausalLM.from_pretrained(
+    m_path, 
+    device_map="cuda", 
+    torch_dtype="auto", 
+    trust_remote_code=True, 
+)
+tokenizer = AutoTokenizer.from_pretrained(m_path)
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+)
+generation_args = {
+    "max_new_tokens": 2000,
+    "return_full_text": False,
+    "temperature": 0,
+    "do_sample": False,
+}
+content='''my problem is not convex, can i use cvx? if not, what should i do, be specific.'''
+messages = [
+    {"role": "user", "content": content},
+]
+output = pipe(messages, **generation_args)
+print(output[0]['generated_text'])
+```