metadata
base_model:
- unsloth/Llama-3.2-3B-Instruct
- bunnycore/Llama-3.2-3b-RRP-lora_model
library_name: transformers
tags:
- mergekit
- merge
Llama-3.2-3B-RRP-V0.1 is a language model based on the Llama 3.2 architecture, specifically the 3B parameter variant. This particular model, bunnycore/Llama-3.2-3B-RRP-V0.1 is a merged model, created using mergekit, from unsloth/Llama-3.2-3B-Instruct and bunnycore/Llama-3.2-3b-RRP-lora_model.
Recommended System Prompt
Always think before doing anything. Remember, your thinking process should be wrapped in <think>/</think> tags, then output your answer after that.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: unsloth/Llama-3.2-3B-Instruct+bunnycore/Llama-3.2-3b-RRP-lora_model
dtype: bfloat16
merge_method: passthrough
models:
- model: unsloth/Llama-3.2-3B-Instruct+bunnycore/Llama-3.2-3b-RRP-lora_model
tokenizer_source: unsloth/Llama-3.2-3B-Instruct