Overview

pandafish-2-7b-32k is a 7 billion parameter language model developed by ichigoberry. It is a merge of two prominent models: Mistral-7B-Instruct-v0.2 and cognitivecomputations/dolphin-2.8-mistral-7b-v02, utilizing the dare_ties merge method via LazyMergekit. The base model for this merge is alpindale/Mistral-7B-v0.2-hf.

Key Capabilities

• Instruction Following: Inherits strong instruction-following capabilities from its merged components, particularly Mistral-7B-Instruct-v0.2.
• General Purpose: Designed for a broad range of conversational and text generation tasks.
• Performance: Achieves competitive scores on various benchmarks, including AGIEval (40.8), GPT4All (73.35), and Bigbench (42.69), demonstrating a balanced performance profile.

Good For

• Chatbots and Conversational AI: Its instruction-tuned nature makes it well-suited for interactive applications.
• Text Generation: Capable of generating coherent and contextually relevant text for various prompts.
• Experimentation: Provides a solid base for further fine-tuning or research due to its merged architecture and readily available quantized versions (GGUF, MLX, EXL2).