Sao10K: MN-12B-Lyra-v4
sao10k/mn-12b-lyra-v4
# MN-12B-Lyra-v4 | Property | Value | | --- | --- | | Author | Sao10K | | License | cc-by-nc-4.0 | | Model Size | 12B parameters | | Base Architecture | Mistral-NeMo | | HuggingFace | [Link](https://huggingface.co/Sao10K/MN-12B-Lyra-v4) | ## What is MN-12B-Lyra-v4? MN-12B-Lyra-v4 is an advanced language model that builds upon previous Lyra versions, specifically designed to enhance instruction following and coherency. It represents a significant evolution in the Lyra series, implementing a unique reinforcement learning approach that targets instruction handling directly on the base NeMo model rather than using traditional SFT-first methodology. ## Implementation Details The model features comprehensive ChatML support and its variants, with specific attention to tokenizer optimization and quantization improvements. It implements a sophisticated sampling strategy with recommended temperature ranges of 0.6-1.0 and crucial min\_p values of 0.1-0.2 for optimal NeMo performance. - Enhanced tokenizer configuration with improved stability - Support for multiple chat template formats - Optimized stopping string handling - Fixed token generation issues while maintaining core functionality ## Core Capabilities - Advanced instruction following and coherency - Flexible chat template support including ChatML and its variants - Improved quantization handling - Robust response generation with optimized sampling parameters ## Frequently Asked Questions ### Q: What makes this model unique? The model's unique approach lies in its direct reinforcement learning implementation targeting instruction and coherency on the base NeMo model, rather than using traditional SFT-first approaches. This has resulted in improved quantization handling and more stable performance. ### Q: What are the recommended use cases? The model is particularly well-suited for applications requiring structured dialogue interactions, thanks to its comprehensive ChatML support and enhanced instruction-following capabilities. It's optimized for scenarios requiring coherent and context-aware responses. ## Related Models 🍰 Interesting in building your own agents? [Infron AI](https://infron.ai/) provides Huggingface integration tools to manage and monitor prompts with your whole team.
Model specifications
- Input
- text
- Output
- text
- Context
- 10,000 tokens
- Max output
- 10,000 tokens
- Input price
- $0 / 1M tokens
- Output price
- $0 / 1M tokens
- Released
- 2026-02-18
Capabilities
- Streaming
- Playground
Frequently asked questions
- What is Sao10K: MN-12B-Lyra-v4?
- # MN-12B-Lyra-v4 | Property | Value | | --- | --- | | Author | Sao10K | | License | cc-by-nc-4.0 | | Model Size | 12B parameters | | Base Architecture | Mistral-NeMo | | HuggingFace | [Link](https://huggingface.co/Sao10K/MN-12B-Lyra-v4) | ## What is MN-12B-Lyra-v4? MN-12B-Lyra-v4 is an advanced language model that builds upon previous Lyra versions, specifically designed to enhance instruction following and coherency. It represents a significant evolution in the Lyra series, implementing a unique reinforcement learning approach that targets instruction handling directly on the base NeMo model rather than using traditional SFT-first methodology. ## Implementation Details The model features comprehensive ChatML support and its variants, with specific attention to tokenizer optimization and quantization improvements. It implements a sophisticated sampling strategy with recommended temperature ranges of 0.6-1.0 and crucial min\_p values of 0.1-0.2 for optimal NeMo performance. - Enhanced tokenizer configuration with improved stability - Support for multiple chat template formats - Optimized stopping string handling - Fixed token generation issues while maintaining core functionality ## Core Capabilities - Advanced instruction following and coherency - Flexible chat template support including ChatML and its variants - Improved quantization handling - Robust response generation with optimized sampling parameters ## Frequently Asked Questions ### Q: What makes this model unique? The model's unique approach lies in its direct reinforcement learning implementation targeting instruction and coherency on the base NeMo model, rather than using traditional SFT-first approaches. This has resulted in improved quantization handling and more stable performance. ### Q: What are the recommended use cases? The model is particularly well-suited for applications requiring structured dialogue interactions, thanks to its comprehensive ChatML support and enhanced instruction-following capabilities. It's optimized for scenarios requiring coherent and context-aware responses. ## Related Models 🍰 Interesting in building your own agents? [Infron AI](https://infron.ai/) provides Huggingface integration tools to manage and monitor prompts with your whole team.
- How much does Sao10K: MN-12B-Lyra-v4 cost?
- Input costs start at $0 / 1M tokens and output costs start at $0 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Sao10K: MN-12B-Lyra-v4?
- Sao10K: MN-12B-Lyra-v4 supports a 10,000 token context window and up to 10,000 output tokens.
- What capabilities does Sao10K: MN-12B-Lyra-v4 support?
- Sao10K: MN-12B-Lyra-v4 supports Streaming, Playground.