Update README.md

README.md

@@ -8,9 +8,9 @@ tags:
 - udkai/Turdus
 ---
 
-# ('Marcoroni-7b-DPO-Merge',)
+# Marcoroni-7b-DPO-Merge
 
-('Marcoroni-7b-DPO-Merge',) is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+Marcoroni-7b-DPO-Merge is a merge of the following models using [mergekit](https://github.com/cg123/mergekit) and inspired by [Maxime Labonne's work](https://medium.com/@mlabonne):
 * [fblgit/UNA-TheBeagle-7b-v1](https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1)
 * [udkai/Turdus](https://huggingface.co/udkai/Turdus)
 
@@ -33,4 +33,44 @@ base_model: madatnlp/marcoroni-7b-v3-safetensor
 parameters:
   normalize: true
 dtype: float16
-```
+```
+
+## 💻 Example Python Code
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+model_name_or_path = "nfaheem/Marcoroni-7b-DPO-Merge"
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
+                                             device_map="auto",
+                                             revision="main")
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+prompt = "Write a story about llamas"
+system_message = "You are a story writing assistant"
+prompt_template=f'''{prompt}
+'''
+
+print("\n\n*** Generate:")
+
+input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
+output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
+print(tokenizer.decode(output[0]))
+
+# Inference can also be done using transformers' pipeline
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    repetition_penalty=1.1
+)
+
+print(pipe(prompt_template)[0]['generated_text'])