Update README.md

README.md

@@ -45,4 +45,20 @@ Fine tuned on a Graphcore IPU-POD64 using `popxl`.
 
 Prompt sentences are tokenized and packed together to form 1024 token sequences, following [HF packing algorithm](https://github.com/huggingface/transformers/blob/v4.20.1/examples/pytorch/language-modeling/run_clm.py). No padding is used.
 Since the model is trained to predict the next token, labels are simply the input sequence shifted by one token.
-Given the training format, no extra care is needed to account for different sequences: the model does not need to know which sentence a token belongs to.
+Given the training format, no extra care is needed to account for different sequences: the model does not need to know which sentence a token belongs to.
+
+## How to use
+The model can be easily loaded using AutoModelForCausalLM.
+Text generation can be implemented or via the pipeline API.
+
+```python
+from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+
+hf_model = AutoModelForCausalLM.from_pretrained("Graphcore/gptj-mnli")
+tokenizer = AutoTokenizer.from_pretrained('EleutherAI/gpt-j-6B')
+generator =  pipeline('text-generation', model=hf_model, tokenizer=tokenizer)
+prompt = "mnli hypothesis: Your contributions were of no help with our students' education." \
+         "premise: Your contribution helped make it possible for us to provide our students with a quality education. target:"
+out = generator(prompt, return_full_text=False, max_new_tokens=5, top_k=1)
+# [{'generated_text': ' contradiction'}]
+```