update mt bench plot & clean up minor typos

README.md

@@ -80,29 +80,27 @@ The dataset is comprised of a mixture of open datasets large-scale datasets avai
 1. SFT Datasets
 - HuggingFaceH4/ultrachat_200k
 - meta-math/MetaMathQA
-- Wizard Dataset
+- WizardLM/WizardLM_evol_instruct_V2_196k
 - Open-Orca/SlimOrca
 2. Preference Datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 - Intel/orca_dpo_pairs
 
-
-### Training Procedure
-
 ## Performance
 
 ### MT-Bench and Alpaca Bench
 
-<img src="https://cdn-uploads.huggingface.co/production/uploads/6310474ca119d49bc1eb0d80/jwpbBHzdCkHm0rMvPUVxC.png" alt="mt_bench_plot" width="600"/>
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/6310474ca119d49bc1eb0d80/8WIZS6dAlu5kSH-382pMl.png" alt="mt_bench_plot" width="600"/>
 
 | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
 |-------------|-----|----|---------------|--------------|
 | **StableLM Zephyr 3B** 🪁 | 3B | DPO | 6.64 | 76.00 |
-| Stable Zephyr (SFT only) | 3B | SFT | 6.04 | 71.15 | 
+| StableLM Zephyr (SFT only) | 3B | SFT | 6.04 | 71.15 | 
 | Capybara v1.9 | 3B | dSFT | 5.94 | - |
 | MPT-Chat |  7B |dSFT |5.42| -|
-| Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
-| Mistral-Instructv0.1 | 7B|  - | 6.84 |-|
+| Xwin-LM v0.1 | 7B| dPPO| 6.19| 87.83|
+| Mistral-Instruct v0.1 | 7B|  - | 6.84 |-|
 | Zephyr-7b-α |7B|  dDPO| 6.88| -|
 | Zephyr-7b-β| 7B | dDPO | 7.34 | 90.60 |
 | Falcon-Instruct |  40B |dSFT |5.17 |45.71|