mistral-large-instruct-2411-int8-w8a8

int8 w8a8 quantized version of mistralai/Mistral-Large-Instruct-2411

Model Card for Mistral-Large-Instruct-2411

Mistral-Large-Instruct-2411 is an advanced dense Large Language Model (LLM) of 123B parameters with state-of-the-art reasoning, knowledge and coding capabilities extending Mistral-Large-Instruct-2407 with better Long Context, Function Calling and System Prompt.

Key features

• Multi-lingual by design: Dozens of languages supported, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch and Polish.
• Proficient in coding: Trained on 80+ coding languages such as Python, Java, C, C++, Javacsript, and Bash. Also trained on more specific languages such as Swift and Fortran.
• Agent-centric: Best-in-class agentic capabilities with native function calling and JSON outputting.
• Advanced Reasoning: State-of-the-art mathematical and reasoning capabilities.
• Mistral Research License: Allows usage and modification for non-commercial usages.
• Large Context: A large 128k context window.
• Robust Context Adherence: Ensures strong adherence for RAG and large context applications.
• System Prompt: Maintains strong adherence and support for more reliable system prompts.

System Prompt

We appreciate the feedback received from our community regarding our system prompt handling.
In response, we have implemented stronger support for system prompts.
To achieve optimal results, we recommend always including a system prompt that clearly outlines the bot's purpose, even if it is minimal.

Basic Instruct Template (V7)

<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST]