Update README.md

README.md

@@ -9,6 +9,7 @@ tags:
 - llama
 - trl
 - finlang
+- qlora
 base_model: unsloth/llama-3-8b-bnb-4bit
 ---
 
@@ -34,7 +35,8 @@ max_seq_length=2048
 model, tokenizer = FastLanguageModel.from_pretrained(
         model_name = "anamikac2708/Llama3-8b-finetuned-investopedia-Merged-FP16", # YOUR MODEL YOU USED FOR TRAINING
         max_seq_length = max_seq_length,
-        dtype = torch.bfloat16
+        dtype = torch.bfloat16,
+        #load_in_4bit = True,  # IF YOU WANT TO LOAD WITH BITSANDBYTES INT4
     )
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
@@ -77,7 +79,7 @@ Hyperparameters:
 }
 ```
 
-Model was trained on 1xA100 80GB, below loss and memory consmuption details:
+## Model was trained on 1xA100 80GB, below loss and memory consmuption details:
 {'eval_loss': 0.9614351987838745, 
 'eval_runtime': 244.0411, 
 'eval_samples_per_second': 2.663,