qanthony-z commited on
Commit
c91f41e
1 Parent(s): c62d006

remove redundant statement

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -10,7 +10,7 @@ Zamba2-1.2B-instruct is obtained from Zamba2-1.2B by fine-tuning on instruction-
10
  1. SFT of the base [Zamba2-1.2B](https://huggingface.co/Zyphra/Zamba2-1.2B) model on [ultrachat_200k](HuggingFaceH4/ultrachat_200k) and [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct)
11
  2. DPO of the SFT checkpoint on [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized), [orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs), and [OpenHermesPreferences](https://huggingface.co/datasets/argilla/OpenHermesPreferences)
12
 
13
- Zamba2-1.2B-Instruct is a hybrid model composed of state-space ([Mamba2](https://github.com/state-spaces/mamba)) and transformer blocks. It is based on the [Zamba2-1.2B](https://huggingface.co/Zyphra/Zamba2-1.2B) architecture.
14
 
15
  ## Quick start
16
 
 
10
  1. SFT of the base [Zamba2-1.2B](https://huggingface.co/Zyphra/Zamba2-1.2B) model on [ultrachat_200k](HuggingFaceH4/ultrachat_200k) and [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct)
11
  2. DPO of the SFT checkpoint on [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized), [orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs), and [OpenHermesPreferences](https://huggingface.co/datasets/argilla/OpenHermesPreferences)
12
 
13
+ Zamba2-1.2B-Instruct is a hybrid model composed of state-space ([Mamba2](https://github.com/state-spaces/mamba)) and transformer blocks.
14
 
15
  ## Quick start
16