"Update README.md"

README.md

@@ -20,16 +20,43 @@ datasets:
 - OpenAssistant/oasst1
 library_name: transformers
 ---
-![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)
+[![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)]()
+
 ## I am still building the structure of these descriptions.
-These will carry increasingly more content to help find the best models for a purpose.
 
-This is a gguf quantized version of
+These will contain increasingly more content to help find the best models for a purpose.
 
-https://huggingface.co/OpenAssistant/falcon-7b-sft-top1-696
+# falcon-7b-sft-top1-696 - GGUF
+- Model creator: [OpenAssistant](https://huggingface.co/OpenAssistant)
+- Original model: [falcon-7b-sft-top1-696](https://huggingface.co/OpenAssistant/falcon-7b-sft-top1-696)
 
-# Original Model Card:
 
+
+# About GGUF format
+
+`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
+A growing list of Software is using it and can therefore use this model.
+The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
+
+# Quantization variants
+
+There is a bunch of quantized files available. How to choose the best for you:
+
+# legacy quants
+
+Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
+Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
+Falcon 7B models cannot be quantized to K-quants.
+
+# K-quants
+
+K-quants are based on the idea that the quantization of certain parts affects the quality in different ways. If you quantize certain parts more and others less, you get a more powerful model with the same file size, or a smaller file size and lower memory load with comparable performance.
+So, if possible, use K-quants.
+With a Q6_K you should find it really hard to find a quality difference to the original model - ask your model two times the same question and you may encounter bigger quality differences.
+
+
+
+# Original Model Card:
 # Open-Assistant Falcon 7B SFT OASST-TOP1 Model
 
 This model is a fine-tuning of TII's [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b) LLM.
@@ -142,4 +169,10 @@ deepspeed trainer_sft.py --configs defaults falcon-7b oasst-top1 --cache_dir <da
 Export command:
 ```
 python export_model.py --dtype bf16 --hf_repo_name OpenAssistant/falcon-7b-sft-top1 --trust_remote_code --auth_token <auth_token> <output_path> --max_shard_size 2GB
-```
+```<center>
+[![GitHub](https://maddes8cht.github.io/assets/buttons/github-io-button.png)](https://maddes8cht.github.io)
+[![Stack Exchange](https://stackexchange.com/users/flair/26485911.png)](https://stackexchange.com/users/26485911)
+[![GitHub](https://maddes8cht.github.io/assets/buttons/github-button.png)](https://github.com/maddes8cht)
+[![HuggingFace](https://maddes8cht.github.io/assets/buttons/huggingface-button.png)](https://huggingface.co/maddes8cht)
+[![Twitter](https://maddes8cht.github.io/assets/buttons/twitter-button.png)](https://twitter.com/maddes1966)
+</center>