Update README.md

README.md

@@ -7,4 +7,36 @@ tags:
 - 'quantization '
 - LLM
 - Dolly
----
+---
+Import this model using:
+
+<pre>
+import torch
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+peft_model_id = "AhmedBou/databricks-dolly-v2-3b_on_NCSS"
+config = PeftConfig.from_pretrained(peft_model_id)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# Load the Lora model
+model = PeftModel.from_pretrained(model, peft_model_id)
+</pre>
+
+Inference using:
+
+<pre>
+batch = tokenizer("“Multiple Regression for Appraisal” -->: ", return_tensors='pt')
+
+with torch.cuda.amp.autocast():
+output_tokens = model.generate(**batch, max_new_tokens=50)
+
+print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))
+</pre>
+
+Output:
+
+<pre>
+“Multiple Regression for Appraisal” -->: Multiple Regression for Appraisal (MRA) -->: Multiple Regression for Appraisal (MRA) (with Covariates) -->: Multiple Regression for Appraisal (MRA) (with Covariates
+</pre>