Update README.md

README.md

@@ -8,7 +8,7 @@ license: other
 # Model Card for ContractAssist model
 
 <!-- Provide a quick summary of what the model is/does. [Optional] -->
-Intruction tuned model using FlanT5-XXL on data generated via ChatGPT for generating and/or modifying the Legal Clauses.
+Instruction tuned FlanT5-XXL on Legal Clauses data generated via ChatGPT. The model is capable for generating and/or modifying the Legal Clauses.
 
 
 
@@ -31,9 +31,8 @@ Intruction tuned model using FlanT5-XXL on data generated via ChatGPT for genera
 
 </details>
 
-### Running the model on a GPU using different precisions
+### Running the model on a GPU in 8bit
 
-#### FP16
 
 <details>
 <summary> Click to expand </summary>
@@ -42,35 +41,20 @@ Intruction tuned model using FlanT5-XXL on data generated via ChatGPT for genera
 # pip install accelerate peft bitsandbytes
 import torch
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
-from peft import PeftModel,PeftConfig 
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", torch_dtype=torch.float16)
-input_text = "translate English to German: How old are you?"
-input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
-outputs = model.generate(input_ids)
-print(tokenizer.decode(outputs[0]))
-```
-
-</details>
-
-#### INT8
+from peft import PeftModel,PeftConfig
+peft_model_id = 'NebulaSense/ContractAssist'
 
-<details>
-<summary> Click to expand </summary>
+peft_config = PeftConfig.from_pretrained(peft_model_id) 
 
-```python
-# pip install bitsandbytes accelerate
-from transformers import T5Tokenizer, T5ForConditionalGeneration
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", load_in_8bit=True)
-input_text = "translate English to German: How old are you?"
-input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
-outputs = model.generate(input_ids)
-print(tokenizer.decode(outputs[0]))
+model =  AutoModelForSeq2SeqLM.from_pretrained(peft_config.base_model_name_or_path, device_map="auto",load_in_8bit=True)
+tokenizer = AutoTokenizer.from_pretrained(peft_config.base_model_name_or_path)
+model = PeftModel.from_pretrained(model, peft_model_id)
+model.eval()
 ```
 
 </details>
 
+
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
 ## Direct Use