Downloads · 30 days
22
35% of all-time downloads
gallantpigeon/mistral-large-instruct-2411-w8a16
mistral-large-instruct-2411-w8a16 is a machine learning model from gallantpigeon. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for vllm. The card lists the license as other.
w8a16 quantized version of mistralai/Mistral-Large-Instruct-2411
Downloads · 30 days
22
35% of all-time downloads
All-time downloads
63
Public
Parameters
123B
123 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors123 GB · 100%
How the weights are stored.
I32122B · 99%
From the Hugging Face model README
w8a16 quantized version of mistralai/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.
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.
<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST]