Update README.md

README.md

@@ -11,7 +11,19 @@ tags:
 A merge of [fblgit/UNA-TheBeagle-7b-v1](https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1), [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca), [samir-fama/FernandoGPT-v1](https://huggingface.co/samir-fama/FernandoGPT-v1) and [Neuronovo/neuronovo-7B-v0.3](https://huggingface.co/Neuronovo/neuronovo-7B-v0.3).
 
 The idea is that these models perform very well in their respective fields, and that they're also likely to work just as well together. I will submit it to the open llm eval, and I will also be testing the q5_k_m version for results.
-
+## Provided files
+
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
+| ---- | ---- | ---- | ---- | ---- | ----- |
+| [Q2_K Tiny](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q2_k.gguf) | Q2_K | 2 | 8.06 GB| 10.06 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Q3_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q3_k_m.gguf) | Q3_K_M | 3 | 10.5 GB| 12.5 GB | very small, high quality loss |
+| [Q4_0](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q4_0.gguf) | Q4_0 | 4 | 13.6 GB| 15.6 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Q4_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q4_k_m.gguf) | Q4_K_M | 4 | ~13.6 GB| ~15.6 GB | medium, balanced quality - recommended |
+| [Q5_0](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q5_0.gguf) | Q5_0 | 5 | 16.6 GB| 18.6 GB | legacy; large, balanced quality |
+| [Q5_K_M](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q5_k_m.gguf) | Q5_K_M | 5 | ~16.6 GB| ~18.6 GB | large, balanced quality - recommended |
+| [Q6 XL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q6_k.gguf) | Q6_K | 6 | 19.8 GB| 21.8 GB | very large, extremely low quality loss |
+| [Q8 XXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-q8_0.gguf) | Q8_0 | 8 | 25.7 GB| 27.7 GB | very large, extremely low quality loss - not recommended |
+| [f16 XXXL](https://huggingface.co/Kquant03/Ryu-4x7B-MoE-GGUF/blob/main/ggml-model-f16.gguf) | f16 | 8 | 48.3 GB| 50.3 GB | very VERY large, extremely low quality loss - not recommended |
 # "[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.)