Model Card: Nous-Hermes-Llama-2-13b-Kimiko-Lora-Merged

This is a Llama 2-based model consisting of Nous Hermes Llama 2 13b (https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) merged with Kimiko Lora (https://huggingface.co/nRuaif/Kimiko_13B) using the provided QLoRA adapter.

The intended objective was to combine NH-L2's reasoning and instruction-following capabilities with Kimiko's character roleplay capabilities.

added_tokens.json was padded with dummy tokens to reach 32 added tokens in order to allow GGML conversion in llama.cpp without error due to vocab size mismatch.

Usage:

Intended to be prompted either with the Alpaca instruction format of the NH-L2 base model:

### Instruction:
<prompt>

### Response:
<leave a newline blank for model to respond>

Or the Kimiko lora instruction format:

<<SYSTEM>>
<character card and system prompt>

<<USER>>
<prompt>

<<AIBOT>>
<leave a newline blank for model to respond>

Bias, Risks, and Limitations

The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.

Training Details

This model is a merge. Please refer to the link repositories of the base model and lora for details.