limcheekin's picture
feat: updated model to q5_1 as q8_0 is too slow.
5041f48
---
title: ToolBench-ToolLLaMA-2-7b-GGML (q5_1)
colorFrom: purple
colorTo: blue
sdk: docker
models:
- ToolBench/ToolLLaMA-2-7b
- s3nh/ToolBench-ToolLLaMA-2-7b-GGML
tags:
- inference api
- openai-api compatible
- llama-cpp-python
- ToolLLaMA-2-7b
- ggml
pinned: false
---
# ToolBench-ToolLLaMA-2-7b-GGML (q5_1)
Please refer to the [index.html](index.html) for more information.