Update README.md

README.md

@@ -3,12 +3,10 @@ license: apache-2.0
 inference: true
 library_name: transformers
 pipeline_tag: text-generation
-
 metrics:
 - rouge
 - bleu
 - bleurt
-
 model-index:
 - name: ibleducation/ibl-tutoring-7B-32k
   results:
@@ -16,33 +14,35 @@ model-index:
       name: truthfulqa_gen
       type: text-generation
     dataset:
-      type: truthful_qa       
-      name: Truthful QA          
+      type: truthful_qa
+      name: Truthful QA
     metrics:
-      - type: bleurt
-        name: bleurt_max
-        value: -0.4572
-      - type: bleurt
-        name: bleurt_acc
-        value: 0.4231 
-      - type: bleurt
-        name: bleurt_diff
-        value: -0.0825 
-      - type: bleu
-        name: bleu_max
-        value:   18.652
-      - type: bleu
-        name: bleu_acc
-        value: 0.4018
-      - type: bleu
-        name: bleu_diff 
-        value: -2.2541
-      - type: rouge
-        name: rouge1_max
-        value: 40.0851
-      - type: rouge
-        name: rougeL_diff
-        value: -4.0046
+    - type: bleurt
+      name: bleurt_max
+      value: -0.4572
+    - type: bleurt
+      name: bleurt_acc
+      value: 0.4231
+    - type: bleurt
+      name: bleurt_diff
+      value: -0.0825
+    - type: bleu
+      name: bleu_max
+      value: 18.652
+    - type: bleu
+      name: bleu_acc
+      value: 0.4018
+    - type: bleu
+      name: bleu_diff
+      value: -2.2541
+    - type: rouge
+      name: rouge1_max
+      value: 40.0851
+    - type: rouge
+      name: rougeL_diff
+      value: -4.0046
+datasets:
+- ibleducation/ibl-best-practices-instructor-dataset
 ---
 
 # ibleducation/ibl-tutoring-7B-32k
@@ -84,7 +84,7 @@ Mistrallite was chosen because its it's performance when compared to Mistral-7B-
 - **Language:** English
 - **Finetuned from weights:** [Mistrallite](https://huggingface.co/amazon/MistralLite)
 - **Finetuned on data:**
-  - ibl-best-practices-instructor-dataset (private)
+  - [ibleducation/ibl-best-practices-instructor-dataset](https://huggingface.co/datasets/ibleducation/ibl-best-practices-instructor-dataset)
 - **Model License:** Apache 2.0
 
 ## How to Use ibl-tutoring-7B-32k from Python Code (HuggingFace transformers) ##
@@ -134,4 +134,4 @@ for seq in sequences:
 **Important** - Use the prompt template below for ibl-tutoring-7B-32k:
 ```
 <|prompter|>{prompt}</s><|assistant|>
-```
+```