Update README.md

README.md

@@ -7,9 +7,9 @@ https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b/blob/main/LIC
 We don't know if it is any good since we have not benched this yet but we are happy for anyone to try it out and give some feedback.
 You can try this model on our API at https://www.awanllm.com/
 
-Trained on 4096 sequence length, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine.
+Trained on 2048 sequence length, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine.
 
-Trained using Cognitive Computations Eric Hartford's https://huggingface.co/datasets/cognitivecomputations/dolphin dataset as I've found great results from their dolphin models in previous Llama models.
+Trained using Cognitive Computations Eric Hartford's https://huggingface.co/datasets/cognitivecomputations/dolphin dataset as we've found great results from their dolphin models in previous Llama models.
 
 Trained for 2 days on 2x RTX3090 on our own machine, using 4-bit loading and Qlora 64-rank 128-alpha resulting in 2% trainable weights.
 
@@ -17,7 +17,7 @@ The goal for this model is to have the model less-censored and great at general
 We started training this BEFORE they launched their own full weight trained Llama-3-8B-Dolphin-2.9 with their own curated datasets and the newer "Dolphin 2.9" dataset.
 https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b
 
-The difference is that we train this using Meta's new Llama 3 instruct format and not the regular ChatML format that Dolphin models are usually trained on.
+The difference is that we train this using Meta's new Llama 3 instruct format and not the regular ChatML format that Dolphin models are usually trained on. This is because we think that it might perform better using the format it was originally trained on.
 Instruct format:
 ```
 <|begin_of_text|><|start_header_id|>system<|end_header_id|>