mylesgoose/Llama-3.2-1B-Instruct-abliterated
mylesgoose/Llama-3.2-1B-Instruct-abliterated is a 1.23 billion parameter instruction-tuned causal language model developed by Meta, part of the Llama 3.2 collection. Optimized for multilingual dialogue use cases, including agentic retrieval and summarization, it supports a 128k context length and was trained on up to 9 trillion tokens. This model excels in assistant-like chat applications across multiple languages, outperforming many open-source and closed chat models on common benchmarks.
Loading preview...
Model Overview
mylesgoose/Llama-3.2-1B-Instruct-abliterated is a 1.23 billion parameter instruction-tuned model from Meta's Llama 3.2 family, designed for multilingual text-in/text-out generative tasks. It utilizes an optimized transformer architecture with Grouped-Query Attention (GQA) and was fine-tuned using Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF) for helpfulness and safety. The model supports a substantial 128k context length and was trained on up to 9 trillion tokens, with a knowledge cutoff of December 2023.
Key Capabilities
- Multilingual Dialogue: Optimized for assistant-like chat and agentic applications in multiple languages, including English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
- Agentic Use Cases: Excels in knowledge retrieval, summarization, mobile AI-powered writing assistants, and query/prompt rewriting.
- Performance: Outperforms many open-source and closed chat models on common industry benchmarks, particularly in multilingual contexts.
- Efficiency: The 1B and 3B models are designed for deployment in constrained environments, such as mobile devices.
Good For
- Developing multilingual chatbots and virtual assistants.
- Implementing agentic systems for information retrieval and text summarization.
- Applications requiring efficient, instruction-tuned language generation in resource-constrained settings.
- Research into safety fine-tuning and robust model deployment.