Update README.md

README.md

@@ -56,4 +56,17 @@ A chat between a curious user and an artificial intelligence assistant. The assi
 Output: ASSISTANT:
 
 ```
-Please note that we still recommend using Vicuna as your preferred Chatbot or Writing Assistant, over Flacuna. Flacuna's primary strength lies in problem-solving tasks, making it ideal for such applications.
+Please note that we still recommend using Vicuna as your preferred Chatbot or Writing Assistant, over Flacuna. Flacuna's primary strength lies in problem-solving tasks, making it ideal for such applications.
+
+The following table presents the writing performance of Flacuna on the IMPACT dataset, which is a component of the InstructEval evaluation suite. The generated responses have been evaluated by ChatGPT, and their relevance and coherence have been scored on a scale of 1 to 5.
+
+
+| **Model** | **Size** | **Informative Rel.** | **Informative Coh.** | **Professional Rel.** | **Professional Coh.** | **Argumentative Rel.** | **Argumentative Coh.** | **Creative Rel.** | **Creative Coh.** | **Avg. Rel.** | **Avg. Coh.** |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| ChatGPT | - | 3.34 | 3.98 | 3.88 | 3.96 | 3.96 | 3.82 | 3.92 | 3.94 | 3.78 | 3.93 |
+| Flan-Alpaca | 11B | 3.56 | 3.46 | 3.54 | 3.70 | 3.22 | 3.28 | 3.70 | 3.40 | 3.51 | 3.46 |
+| Flan-T5 | 11B | 2.64 | 3.24 | 2.62 | 3.22 | 2.54 | 3.40 | 2.50 | 2.72 | 2.58 | 3.15 |
+| Dolly-V2 | 12B | 3.54 | 3.64 | 2.96 | 3.74 | 3.66 | 3.20 | 3.02 | 3.18 | 3.30 | 3.44 |
+| StableVicuna | 13B | 3.54 | 3.64 | 2.96 | 3.74 | 3.30 | 3.20 | 3.02 | 3.18 | 3.21 | 3.44 |
+| Vicuna | 13B | 3.60 | 3.96 | 3.74 | 3.82 | 3.82 | 3.56 | 3.82 | 3.92 | 3.75 | 3.82 |
+| Flacuna | 13B | 3.02 | 3.42 | 3.48 | 3.52 | 3.38 | 3.02 | 3.92 | 3.80 | 3.45 | 3.44 |