Mixtral-8x7B-Instruct-v0.1-w4a16-llmcompressor

Description

Mixtral-8x7B-Instruct-v0.1-w4a16-llmcompressor is an open-weight text-generation model with roughly 7B parameters published by amd on the Hugging Face Hub. It has 753 downloads. Runs with transformers.

Categories

• Productivity

Tags

• mixtral
• text-generation
• quantized
• int4
• w4a16
• weight-only
• 4-bit
• llm-compressor

Capabilities

• Text generation
• Conversational
• Library: transformers
• 7B parameters