improve readme clarity and formatting

README.md

@@ -13,10 +13,11 @@ quantized_by: Tanvir1337
 ---
 # Tanvir1337/Mistral-v0.2-Nexus-Internal-Knowledge-Map-7B-GGUF
 
-Quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp/).
+This model has been quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp/), a high-performance inference engine for large language models.
 
-## System Prompt
+## System Prompt Format
 
+To interact with the model, use the following prompt format:
 ```
 {System}
 ### Prompt:
@@ -24,36 +25,32 @@ Quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp/).
 ### Response:
 ```
 
-## Usage
+## Usage Instructions
 
-If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF) for details.
+If you're new to using GGUF files, refer to [TheBloke's README](https://huggingface.co/TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF) for detailed instructions.
 
-## Quants
+## Quantization Options
 
-Here is a handy graph comparing some quant types (lower is better):
+The following graph compares various quantization types (lower is better):
 
 ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
 
-[Artefact2's](https://github.com/Artefact2) thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+For more information on quantization, see [Artefact2's notes](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9).
 
-## Which file should you choose
+## Choosing the Right Model File
 
-The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+To select the optimal model file, consider the following factors:
 
-If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+1. **Memory constraints**: Determine how much RAM and/or VRAM you have available.
+2. **Speed vs. quality**: If you prioritize speed, choose a model that fits within your GPU's VRAM. For maximum quality, consider a model that fits within the combined RAM and VRAM of your system.
 
-If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+**Quantization formats**:
 
-Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+* **K-quants** (e.g., Q5_K_M): A good starting point, offering a balance between speed and quality.
+* **I-quants** (e.g., IQ3_M): Newer and more efficient, but may require specific hardware configurations (e.g., cuBLAS or rocBLAS).
 
-If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+**Hardware compatibility**:
 
-If you want to get more into the weeds, you can check out this extremely useful feature chart:
+* **I-quants**: Not compatible with Vulcan (AMD). If you have an AMD card, ensure you're using the rocBLAS build or a compatible inference engine.
 
-[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
-
-But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
-
-These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
-
-The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
+For more information on the features and trade-offs of each quantization format, refer to the [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix).