Update README.md

README.md

@@ -1,4 +1,45 @@
 ---
 datasets:
 - Abirate/english_quotes
----
+pipeline_tag: text-generation
+---
+
+# How to run in Google Colab
+
+Note: must be run in GPU
+```python
+!pip install -q -U bitsandbytes
+!pip install -q -U git+https://github.com/huggingface/transformers.git 
+!pip install -q -U git+https://github.com/huggingface/peft.git
+```
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+
+model_id = "EleutherAI/gpt-neox-20b"
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
+```
+```python
+from peft import LoraConfig, get_peft_model
+
+lora_config = LoraConfig.from_pretrained('suarkadipa/gpt-neox-20b-english-quotes')
+model = get_peft_model(model, lora_config)
+```
+```python
+text = "Yaya Toure "
+device = "cuda:0"
+
+inputs = tokenizer(text, return_tensors="pt").to(device)
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+#output example: Yaya Touré was born in the Ivory Coast, but moved to France at the age
+```