GPTQ 4-bit no actor version for compatibility that works in textgen-webui
Generated by using scripts from https://gitee.com/yhyu13/llama_-tools
Original weights: https://huggingface.co/openaccess-ai-collective/manticore-13b
Manticore is by far the most satisfying LLaMA model I've used due to its fine-tuning datasets are generated from the best of Vicuna, Wizard, and ShareGPT/GPT4.
Here is a conversation generated in textgen-webui, it shows step by step Chain of Thoughts comments along side generating complex code sample in an engaging tone!
- Downloads last month
- 1,265
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support