uukuguy/speechless-llama2-13b
uukuguy/speechless-llama2-13b is a 13 billion parameter language model, merging Open-Orca/OpenOrca-Platypus2-13B and WizardLM/WizardLM-13B-V1.2, built upon the Llama 2 architecture by Meta. It features a 4096-token context length and demonstrates strong performance across various benchmarks, including ARC, HellaSwag, and MMLU. This model is optimized for general-purpose instruction following and dialogue use cases, accepting the Alpaca instruction format.
Loading preview...
Model Overview
uukuguy/speechless-llama2-13b is a 13 billion parameter language model derived from the Llama 2 family, developed by Meta. This specific version is a merge of Open-Orca/OpenOrca-Platypus2-13B and WizardLM/WizardLM-13B-V1.2, designed for enhanced instruction following capabilities. It supports a context length of 4096 tokens and is available in various quantized formats (GPTQ, GGUF, GGML) for flexible deployment on different hardware.
Key Capabilities
- Instruction Following: Optimized to respond effectively to instructions, utilizing the Alpaca instruction format.
- General-Purpose Text Generation: Capable of generating coherent and relevant text for a wide array of prompts.
- Benchmark Performance: Achieves competitive scores on academic benchmarks, including:
- ARC: 62.03
- HellaSwag: 81.85
- MMLU: 58.52
- TruthfulQA: 55.7
- Average: 64.52
Intended Use Cases
This model is suitable for commercial and research applications requiring robust language understanding and generation in English. It is particularly well-suited for:
- Assistant-like Chatbots: Engaging in dialogue and providing helpful responses.
- Code Generation: As demonstrated by its ability to implement programming tasks like linked lists in C++.
- Natural Language Generation Tasks: Adapting to various tasks where text output is required based on given instructions.