From fb8377d81ea5879f04bbe903be3d186f287ddef9 Mon Sep 17 00:00:00 2001
From: Robin Davidsson <RDson@users.noreply.huggingface.co>
Date: Wed, 15 May 2024 17:38:49 +0000
Subject: [PATCH] Create README.md

---
 README.md | 93 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 93 insertions(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..9549f1b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,93 @@
+---
+tags:
+- moe
+- llama
+- '3'
+- llama 3
+- 2x8b
+---
+# GGUF files of [Llama-3-Magenta-Instruct-4x8B-MoE](https://huggingface.co/RDson/Llama-3-Magenta-Instruct-4x8B-MoE)
+<img src="https://i.imgur.com/c1Mv8cy.png" width="640"/>
+
+# Llama-3-Magenta-Instruct-4x8B-MoE
+This is a experimental MoE created from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B), [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) and [Muhammad2003/Llama3-8B-OpenHermes-DPO](https://huggingface.co/Muhammad2003/Llama3-8B-OpenHermes-DPO) using Mergekit.
+
+Mergekit yaml file:
+```
+base_model: Meta-Llama-3-8B-Instruct
+experts:
+  - source_model: Meta-Llama-3-8B-Instruct
+    positive_prompts:
+    - "explain"
+    - "chat"
+    - "assistant"
+    - "think"
+    - "roleplay"
+    - "versatile"
+    - "helpful"
+    - "factual"
+    - "integrated"
+    - "adaptive"
+    - "comprehensive"
+    - "balanced"
+    negative_prompts:
+    - "specialized"
+    - "narrow"
+    - "focused"
+    - "limited"
+    - "specific"
+  - source_model: ChatQA-1.5-8B
+    positive_prompts:
+    - "python"
+    - "math"
+    - "solve"
+    - "code"
+    - "programming"
+    negative_prompts:
+    - "sorry"
+    - "cannot"
+    - "factual"
+    - "concise"
+    - "straightforward"
+    - "objective"
+    - "dry"
+  - source_model: SFR-Iterative-DPO-LLaMA-3-8B-R
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "AI"
+    - "instructive"
+    - "clear"
+    - "directive"
+    - "helpful"
+    - "informative"
+  - source_model: Llama3-8B-OpenHermes-DPO
+    positive_prompts:
+    - "analytical"
+    - "accurate"
+    - "logical"
+    - "knowledgeable"
+    - "precise"
+    - "calculate"
+    - "compute"
+    - "solve"
+    - "work"
+    - "python"
+    - "code"
+    - "javascript"
+    - "programming"
+    - "algorithm"
+    - "tell me"
+    - "assistant"
+    negative_prompts:
+    - "creative"
+    - "abstract"
+    - "imaginative"
+    - "artistic"
+    - "emotional"
+    - "mistake"
+    - "inaccurate"
+gate_mode: hidden
+dtype: float16
+```
+Some inspiration for the Mergekit yaml file is from [LoneStriker/Umbra-MoE-4x10.7-2.4bpw-h6-exl2](https://huggingface.co/LoneStriker/Umbra-MoE-4x10.7-2.4bpw-h6-exl2).
\ No newline at end of file