• Please note this model was not trained on the rombodawg/LosslessMegaCodeTrainingV3_MINI dataset, despite the name similarity. You can find the training data at the bottom of the model card labeled (megacode2-min100)

• This model was made as a colaboration between me and andreaskoepf who is an affiliate of Open Assistant.

• https://tju01.github.io/FastEval-OpenAssistant/

• chatml format is used: "<|im_start|>system\n{system message}<|im_end|>\n<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"

<|im_start|>system
{system message}<|im_end|>
<|im_start|>user
{user prompt}<|im_end|>
<|im_start|>assistant
{Assistant answer}<|im_end|>

• System prompt

<|im_start|>system
"Below is an instruction that describes a task. Write a response that appropriately completes the request."

• Prompt template

<|im_end|>
<|im_start|>user
"%1"<|im_end|>
<|im_start|>assistant

• user:

  <|im_start|>user
  {User string}<|im_end|>

• bot:

  <|im_start|>assistant
  {Bot string}<|im_end|>

• turn_template:

• context:

  <|im_start|>system
  Below is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>

• https://huggingface.co/TheBloke/LosslessMegaCoder-Llama2-13B-Mini-GPTQ

• https://wandb.ai/open-assistant/epfl-mt-sft/runs/run34_megacode2_min100_13b

• https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored

• https://huggingface.co/datasets/andreaskoepf/megacode2-min100

• https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100

Open LLM Leaderboard Evaluation Results