Update README.md

README.md

@@ -2,22 +2,22 @@
 tags:
 - LoRA
 - QLoRa
-- LoRA Adapter
+- Merged LoRA Model
 model-index:
-- name: sql-guanaco-13b-4
+- name: sql-guanaco-13b-merged
   results: []
 datasets:
-- richardr1126/spider-sql_guanaco_style
+- richardr1126/sql-create-context_guanaco_style
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# sql-guanaco-13b-4
+# sql-guanaco-13b-merged
 
-This is a LoRA adapter for [richardr1126/guanaco-13b-merged](https://huggingface.co/richardr1126/guanaco-13b-merged), or any other merged guanaco-13b model, fine tuned from LLaMA.
+This is a merged LoRA model that can be used with AutoModelForCausalLM or LlamaModelForCausalLM. It is a combination of [richardr1126/guanaco-13b-merged](https://huggingface.co/richardr1126/guanaco-13b-merged) + [richardr1126/lora-sql-guanaco-13b-adapter](https://huggingface.co/richardr1126/lora-sql-guanaco-13b-adapter).
 <br>
-This LoRA was fine-tuned on [richardr1126/sql-create-context_guanaco_style](https://huggingface.co/datasets/richardr1126/sql-create-context_guanaco_style).
+This LoRA was fine-tuned using QLoRA techniques on the [richardr1126/sql-create-context_guanaco_style](https://huggingface.co/datasets/richardr1126/sql-create-context_guanaco_style) dataset.
 
 ### Training hyperparameters