"Update README.md"

README.md

@@ -1,50 +1,50 @@
 ---
-inference: false
-license: apache-2.0
-model_creator: tiiuae
-model_link: https://huggingface.co/tiiuae/falcon-40b-instruct
-model_name: Falcon 40B Instruct
-model_type: falcon
-pipeline_tag: text-generation
-quantized_by: maddes8cht
 datasets:
 - tiiuae/falcon-refinedweb
 language:
 - en
-tags:
-- falcon
+inference: false
+license: apache-2.0
 ---
-![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.
 
-Tiiuae-Falcon 40B instruct is the original instruction following Falcon model from Tiiuae, converted to gguf format.
+These will contain increasingly more content to help find the best models for a purpose.
 
----
-# Falcon 40B Instruct - gguf
+# falcon-40b-instruct - GGUF
 - Model creator: [tiiuae](https://huggingface.co/tiiuae)
-- Original model: [Falcon 40b Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct)
+- Original model: [falcon-40b-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct)
 
----
-<details>
-<summary> Table of contents
+Tiiuae-Falcon 40B instruct is the original instruction following Falcon model from Tiiuae, converted to gguf format.
+
+
+
+# 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:
 
-</summary>
+# 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.
 
-# Table of contents
+# K-quants
 
-[Original Model Card](#original-model-card-by-tiiuae)
+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.
 
-</details>
 
-<details>
-<summary> Original Model Card by tiiuae
-</summary>
-  
-# Original Model Card by tiiuae
-[***Link to original model card***](https://huggingface.co/tiiuae/falcon-40b-instruct)
 
+# Original Model Card:
 # ✨ Falcon-40B-Instruct
 
 **Falcon-40B-Instruct is a 40B parameters causal decoder-only model built by [TII](https://www.tii.ae) based on [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) and finetuned on a mixture of [Baize](https://github.com/project-baize/baize-chatbot). It is made available under the Apache 2.0 license.**
@@ -257,4 +257,10 @@ To cite the [Baize](https://github.com/project-baize/baize-chatbot) instruction
 Falcon-40B-Instruct is made available under the Apache 2.0 license.
 
 ## Contact
-falconllm@tii.ae
+falconllm@tii.ae<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>