This model is a Llama2-7B model finetuned on the union of ShareGPT, the exams dataset and a subset of the Orca dataset. The finetuning was performed with DeepSpeed Chat toolkit (step 1, sft). The model run for three epochs before reaching a plateau on the validation dataset. We used a cosine scheduler, with an initial LR of 2e-5.
- Downloads last month
- 1,158