Update README.md

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 language:
 - en
 pipeline_tag: conversational
+datasets:
+- ayoolaolafenwa/sft-data
 ---
 
 ## ChatLM 
@@ -24,7 +26,7 @@ model_path = "ayoolaolafenwa/ChatLM"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
 model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code = True,
-torch_dtype=torch.bfloat16)
+torch_dtype=torch.bfloat16).to("cuda")
 
 prompt = "<user>: Give me a financial advise on investing in stocks. <chatbot>: "
 
@@ -132,5 +134,4 @@ Check the the modified dataset https://huggingface.co/datasets/ayoolaolafenwa/sf
 
 ChatLM was supervised finetuned with pretrained [Falcon 1-Billion parameters model](https://huggingface.co/tiiuae/falcon-rw-1b) trained on 350-Billion tokens 
 of RefinedWeb. It was trained with a single H100 GPU for 1 epoch. It achieves Perplexity *1.738*.  Check the full code for supervised finetune 
-training on its github repository https://github.com/ayoolaolafenwa/ChatLM/tree/main
-
+training on its github repository https://github.com/ayoolaolafenwa/ChatLM/tree/main