Updated model card to reflect changes to model.

README.md

@@ -17,7 +17,7 @@ the case with the baseline.
 
 The architecture of this LoRA model follows that of the LLaMA-7b Alpaca-LoRA with the hyper-parameters:
 ```
-LORA_R = 16
+LORA_R = 8
 LORA_ALPHA = 16
 LORA_DROPOUT= 0.05
 LORA_TARGET_MODULES = [
@@ -28,8 +28,24 @@ LORA_TARGET_MODULES = [
 ]
 ```
 The model was trained using PEFT for up to 3 epochs, with <code>load_best_model_at_end=True</code> set.
+The learning rate was set to 5e-5, so the minimal validation loss occurred very near to the end of training.
+
+Both the combined model and adapter weights are available.
+
+The combined model can be loaded and used right out of the box:
+```
+BASE_MODEL = "StarFish-DocOracle"
+
+model = LlamaForCausalLM.from_pretrained(
+    BASE_MODEL,
+    torch_dtype=torch.float16,
+    device_map="sequential"
+)
+tokenizer = LlamaTokenizer.from_pretrained(BASE_MODEL)
+```
+
+The adapter can be recombined with the baseline model to generate text:
 
-It can be recombined with the baseline model to generate text:
 ```
 BASE_MODEL = "openlm-research/open_llama_7b_700bt_preview"
 
@@ -39,7 +55,6 @@ bmodel = LlamaForCausalLM.from_pretrained(
     device_map="sequential"
 )
 
-
 peft_model_id = "starfishmedical/SFDocumentOracle-open_llama_7b_lora"
 tokenizer = LlamaTokenizer.from_pretrained(peft_model_id)