This is an AWQ (4-bit) quantized version of Mistral-7B-Instruct-v0.3. It maintains strong instruction-following capabilities while using much less memory than the original model. The model uses a specific chat template and is suitable for local deployment using Transformers or compatible inference engines.
Mistral 7B Instruct sits in PulseGate's Foundation models & chat category. It focuses on running high-quality 7B instruction models with significantly reduced GPU memory usage. It is built as an open-source project for developers. Mistral 7B Instruct is open source under the AGPL-3.0 license. Mistral 7B Instruct is available on the web, the command line, and API.
solidrust builds and maintains Mistral 7B Instruct, and the product first shipped in 2022. Development happens publicly on GitHub with 47.5k stars and 116 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 8 similar tools. Key capabilities include Instruction-tuned LLM, AWQ quantization, and chat template.
Latest indexed changes and source events
solidrust/Mistral-7B-Instruct-v0.3-AWQ verified by the PulseGate indexer
