Update README.md

README.md

@@ -22,11 +22,11 @@ license: apache-2.0
 
 # Mistral-Nemo-Instruct-12B-iMat-GGUF
 
-<b>Important Note: Inferencing is *only* available on this fork of llama.cpp at the moment: https://github.com/ggerganov/llama.cpp/pull/8604 
+<b>Important Note: Inferencing is *only* available on this fork of llama.cpp at the moment: https://github.com/iamlemec/llama.cpp/tree/mistral-nemo (All credits to iamlemec for his work on Mistral-Nemo support)
 
 Other front-ends like the main branch of llama.cpp, kobold.cpp, and text-generation-web-ui may not work as intended</b>
 
-Quantized from fp16.
+Quantized from Mistral-Nemo-Instruct-2407 fp16.
 * Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 92 chunks and n_ctx=512
 * Static fp16 will also be included in repo
 
@@ -39,6 +39,11 @@ For a brief rundown of iMatrix quant performance please see this [PR](https://gi
 [<img src="https://i.imgur.com/mV0nYdA.png" width="920"/>](https://i.imgur.com/mV0nYdA.png)
 
 
-<b>Tips:</b> There's no need to download the entire repo, just pick one of the GGUF files. 
+<b>Tip:</b> If you are getting a `cudaMalloc failed: out of memory` error, try passing an argument for lower context in llama.cpp, e.g. for 8k: `-c 8192`
+
+If you have all ampere generation or newer cards, you can use flash attention like so: `-fa`
+
+Provided Flash Attention is enabled you can also use quantized cache to save on VRAM e.g. for 8-bit: `-ctk q8_0 -ctv q8_0`
+
 
 Original model card can be found [here](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)