Update README.md

README.md

@@ -1,11 +1,26 @@
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/QkbFYjmpqCKfCyWnF-rwf.png)
+(Image credit goes to [NeuralNovel](https://huggingface.co/NeuralNovel))
 
-# Making frankenMoEs more than just a meme...
+# Making frankenMoEs more than just a meme...(this is the GGUF version, to be compiled using Llama.cpp model loader on OOBA or VLLm or something...)
 
 I was approached with the idea to make a merge based on story telling, and considering frankenMoE's tendency to be hallucinatory, I thought that was a wonderful idea. However, I wanted it to be more than just a "meme model". I wanted to make something that would actually work...so we decided to use [SanjiWatsuki/Loyal-Macaroni-Maid-7B](https://huggingface.co/SanjiWatsuki/Loyal-Macaroni-Maid-7B) as a base, [cognitivecomputations/dolphin-2.6-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b) as two of the four experts in order to stabilize it, [SanjiWatsuki/Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B) in order to improve its logical reasoning, and [NeuralNovel/Panda-7B-v0.1](https://huggingface.co/NeuralNovel/Panda-7B-v0.1) to improve its creativity and nuanced storytelling mechanics.
 
 We believe that this, while it might not be better logically than mixtral base instruct, is definitely more creative. Special thanks to [NeuralNovel](https://huggingface.co/NeuralNovel) for collaborating with me on this project
 
+## Provided files
+
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
+| ---- | ---- | ---- | ---- | ---- | ----- |
+| [mixtral-8x7b-v0.1.Q2_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q2_K.gguf) | Q2_K | 2 | 7.87 GB| 9.94 GB | smallest, significant quality loss - not recommended for most purposes |
+| [mixtral-8x7b-v0.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 10.28 GB| 12.47 GB | very small, high quality loss |
+| [mixtral-8x7b-v0.1.Q4_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_0.gguf) | Q4_0 | 4 | 13.30 GB| 15.43 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [mixtral-8x7b-v0.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_M.gguf) | Q4_K_M | 4 | 13.32 GB| 15.73 GB | medium, balanced quality - recommended |
+| [mixtral-8x7b-v0.1.Q5_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q5_0.gguf) | Q5_0 | 5 | 16.24 GB| 18.64 GB | legacy; large, balanced quality |
+| [mixtral-8x7b-v0.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q4_K_M.gguf) | Q5_K_M | 5 | 16.25 GB| ~18.64 GB | large, balanced quality - recommended |
+| [mixtral-8x7b-v0.1.Q6_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q6_K.gguf) | Q6_K | 6 | 19.35 GB| 21.52 GB | very large, extremely low quality loss |
+| [mixtral-8x7b-v0.1.Q8_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF/blob/main/mixtral-8x7b-v0.1.Q8_0.gguf) | Q8_0 | 8 | 25.06 GB| 27.43 GB | very large, extremely low quality loss - not recommended |
+
+**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
 # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
 ### (from the MistralAI papers...click the quoted question above to navigate to it directly.)