| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - Trelis/Llama-2-7b-chat-hf-function-calling-v3 | |
| - xalss/Qwen2-7B-Instruct-glaive-function-calling | |
| - InterSync/Mistral-7B-Instruct-v0.2-Function-Calling | |
| - NousResearch/Hermes-2-Pro-Mistral-7B | |
| # Uma-4x7B-MoE-Function-calling-v0.2 | |
| Hey there! 👋 Welcome to the Uma-4x7B-MoE-Function-calling-v0.2! This is a merge of multiple models brought together using the awesome [VortexMerge kit](https://colab.research.google.com/drive/1YjcvCLuNG1PK7Le6_4xhVU5VpzTwvGhk#scrollTo=UG5H2TK4gVyl). | |
| Let's see what we've got in this merge: | |
| * [Trelis/Llama-2-7b-chat-hf-function-calling-v3](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v3) 🚀 | |
| * [xalss/Qwen2-7B-Instruct-glaive-function-calling](https://huggingface.co/xalss/Qwen2-7B-Instruct-glaive-function-calling) 🚀 | |
| * [InterSync/Mistral-7B-Instruct-v0.2-Function-Calling](https://huggingface.co/InterSync/Mistral-7B-Instruct-v0.2-Function-Calling) 🚀 | |
| * [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) 🚀 | |
| ## 🧩 Configuration | |
| ```yaml | |
| models: | |
| - model: Trelis/Llama-2-7b-chat-hf-function-calling-v3 | |
| parameters: | |
| weight: 0.30 | |
| - model: xalss/Qwen2-7B-Instruct-glaive-function-calling | |
| parameters: | |
| weight: 0.60 | |
| - model: InterSync/Mistral-7B-Instruct-v0.2-Function-Calling | |
| parameters: | |
| weight: 0.90 | |
| - model: NousResearch/Hermes-2-Pro-Mistral-7B | |
| parameters: | |
| weight: 1.0 | |
| merge_method: linear | |
| dtype: float16 | |