Update README.md

README.md

@@ -1,3 +1,68 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- diffusion
+- text generation
+- code generation
+---
+# CoDA-v0-Instruct
+
+## Overview
+CoDA is Salesforce AI Research's open, lightweight and diffusion-based language model.
+
+[Technical Report (Coming soon)]()
+
+[Code](https://github.com/SalesforceAIResearch/CoDA/)
+
+
+
+## Requirements
+```
+torch==2.8.0
+transformers>=4.47.1
+flash-attn==2.8.3
+```
+
+## Quickstart
+Here is a code snippet for loading the model, tokenizer and run generation.
+```python
+import torch
+from transformers import AutoModel, AutoTokenizer
+
+model_name = "Salesforce/CoDA-v0-Instruct"
+device = "cuda"
+
+model = AutoModel.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True).to(device)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model.eval()
+
+prompt = "Write a python function to find the Fibonacci sequence up to n numbers."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+input_ids = tokenizer([text], return_tensors="pt").input_ids.to(model.device)
+generated_ids = model.diffusion_generate(
+    inputs=input_ids,
+    max_new_tokens=256,
+    steps=256,
+    top_p=0.9,
+    temperature=0.2,
+    alg="entropy",
+    alg_temp=0.2,
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(input_ids, generated_ids)
+]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+
+### Deployment
+For deployment, please checkout our repo.