Update README.md

README.md

@@ -53,6 +53,99 @@ The models are made available under a non-commercial CC BY-NC 4.0 license. More
 
 The GALACTICA models are trained on 106 billion tokens of open-access scientific text and data. This includes papers, textbooks, scientific websites, encyclopedias, reference material, knowledge bases, and more. We tokenize different modalities to provide a natural langauge interface for different tasks. See the README.md for more information. See the paper for full information on the training data.
 
+## How to use
+
+Find below some example scripts on how to use the model in `transformers`:
+
+## Using the Pytorch model
+
+### Running the model on a CPU
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+
+from transformers import AutoTokenizer, OPTForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-125m")
+model = OPTForCausalLM.from_pretrained("facebook/galactica-125m")
+
+input_text = "The Transformer architecture [START_REF]"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids
+
+outputs = model.generate(input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+</details>
+
+### Running the model on a GPU
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+# pip install accelerate
+from transformers import AutoTokenizer, OPTForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-125m")
+OPTForCausalLM.from_pretrained("facebook/galactica-125m", device_map="auto")
+
+input_text = "The Transformer architecture [START_REF]"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
+
+outputs = model.generate(input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+</details>
+
+### Running the model on a GPU using different precisions
+
+#### FP16
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+# pip install accelerate
+import torch
+from transformers import AutoTokenizer, OPTForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-125m")
+model = OPTForCausalLM.from_pretrained("facebook/galactica-125m", device_map="auto", torch_dtype=torch.float16)
+
+input_text = "The Transformer architecture [START_REF]"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
+
+outputs = model.generate(input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+</details>
+
+#### INT8
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+# pip install bitsandbytes accelerate
+from transformers import AutoTokenizer, OPTForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-125m")
+model = OPTForCausalLM.from_pretrained("facebook/galactica-125m", device_map="auto", load_in_8bit=True)
+
+input_text = "The Transformer architecture [START_REF]"
+input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
+
+outputs = model.generate(input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+</details>
+
 ## Performance and Limitations
 
 The model outperforms several existing language models on a range of knowledge probes, reasoning, and knowledge-intensive scientific tasks. This also extends to general NLP tasks, where GALACTICA outperforms other open source general language models. That being said, we note a number of limitations in this section.