• Model creator: https://huggingface.co/Weyaxi/
• Original model: https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp/

Original model description:

• name: OpenHermes-2.5-neural-chat-v3-3-Slerp results:
  • task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
    • type: acc_norm value: 68.09 name: normalized accuracy
  • task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
    • type: acc_norm value: 86.2 name: normalized accuracy
  • task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
    • type: acc value: 64.26 name: accuracy
  • task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
    • type: mc2 value: 62.78
  • task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
    • type: acc value: 79.16 name: accuracy
  • task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
    • type: acc value: 67.78 name: accuracy tags:
• merge base_model:
• teknium/OpenHermes-2.5-Mistral-7B
• Intel/neural-chat-7b-v3-3

OpenHermes-2.5-neural-chat-v3-3-Slerp

Prompt Templates

ChatML (OpenHermes-2.5-Mistral-7B):

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

neural-chat-7b-v3-3:

### System:
{system}
### User:
{user}
### Assistant:

Yaml Config to reproduce

Quantizationed versions

GPTQ

• TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-GPTQ

GGUF

• TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF

AWQ

• TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-AWQ

Open LLM Leaderboard Evaluation Results