Update README.md

README.md

@@ -1,9 +1,11 @@
 ---
 datasets:
 - HuggingFaceH4/ultrachat_200k
-- HuggingFaceH4/ultrafeedback_binarized
+- allenai/ultrafeedback_binarized_cleaned
 - meta-math/MetaMathQA
 - WizardLM/WizardLM_evol_instruct_V2_196k
+- openchat/openchat_sharegpt4_dataset
+- LDJnr/Capybara
 - Intel/orca_dpo_pairs
 language:
 - en
@@ -17,16 +19,16 @@ extra_gated_fields:
   I ALLOW Stability AI to email me about new model releases: checkbox
 license: other
 ---
-# `StableLM Zephyr 3B`
+# `StableLM 2 Zephyr 1.6B`
 
 ## Model Description
 
-`StableLM Zephyr 3B` is a 3 billion parameter instruction tuned inspired by [HugginFaceH4's Zephyr 7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) training pipeline this model was trained on a mix of publicly available datasets, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290), evaluation for this model based on
-[MT Bench](https://tatsu-lab.github.io/alpaca_eval/) and [Alpaca Benchmark](https://tatsu-lab.github.io/alpaca_eval/)
+`StableLM 2 Zephyr 1.6B` is a 1.6 billion parameter instruction tuned inspired by [Stablelm Zephyr 1.6B](https://huggingface.co/stabilityai/stablelm-zephyr-3b) training pipeline this model was trained on a mix of publicly available datasets, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290), evaluation for this model based on
+[MT Bench](https://huggingface.co/spaces/lmsys/mt-bench).
 
 ## Usage
 
-`StableLM Zephyr 3B` uses the following instruction format:
+`StableLM 2 Zephyr 1.6B` uses the following instruction format:
 ```
 <|user|>
 List 3 synonyms for the word "tiny"<|endoftext|>