Update README.md

README.md

@@ -54,6 +54,15 @@ reference-data-model:
         https://github.com/tomaarsen/attention_sinks
         https://arxiv.org/abs/2309.17453
 
+  TRL:
+    - Link:
+        https://huggingface.co/docs/trl/index
+        https://huggingface.co/docs/trl/sft_trainer
+
+  flash-attention:
+        https://github.com/Dao-AILab/flash-attention
+        https://arxiv.org/abs/2205.14135
+
   Version:
     - Link:
         https://huggingface.co/NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v1
@@ -113,6 +122,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id,
                                              torch_dtype=torch.bfloat16,
                                              load_in_4bit=True,
                                              low_cpu_mem_usage= True,
+                                             #use_flash_attention_2=True, #GPU A100 or GPU supported
 
                                              attention_sink_size=4,
                                              attention_sink_window_size=1024, #512, # <- Low for the sake of faster generation