docs: enhance style

This commit is contained in:
hieu-jan 2024-03-02 15:14:14 +09:00
parent bbdcabda3e
commit 833c1b2f31

View File

@ -95,7 +95,7 @@ This final model is publicly available at https://huggingface.co/jan-hq/nitro-v1
![Using LLM locally](assets/nitro-on-jan.png) ![Using LLM locally](assets/nitro-on-jan.png)
_Figure 3._ Using the new finetuned model in [Jan](https://jan.ai/) _Figure 3._ Using the new finetuned model in [Jan](https://jan.ai/).
## Improving Results With Rag ## Improving Results With Rag
@ -111,7 +111,7 @@ We curated a new set of [50 multiple-choice questions](https://github.com/janhq/
_Figure 4._ Comparison between fine-tuned model and OpenAI's GPT. _Figure 4._ Comparison between fine-tuned model and OpenAI's GPT.
_Table 1._ Result of the Benchmarking. _Table 1._ Result of Benchmarking Different Model With RAG.
| Approach | Performance | | Approach | Performance |
| ----------------------------------------------------------------------------------- | ----------- | | ----------------------------------------------------------------------------------- | ----------- |
| GPT-3.5 with RAG | 56.7% | | GPT-3.5 with RAG | 56.7% |