Update README.md

more weights. tag. misspelling

README.md

@@ -5,6 +5,8 @@ license_name: mnpl
 license_link: https://mistral.ai/licences/MNPL-0.1.md
 tags:
 - code
+- text-generation-inference
+- mistral
 language:
 - code
 ---
@@ -27,17 +29,17 @@ python3 convert.py -i ~/models/Codestral-22B-v0.1-hf/ -o /tmp/exl2/ -nr -m ~/mod
 ```
 
 ## Quantization
-- [3.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/3_0) 
+- [3.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/3_0) 8.75gb
 - [4.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/4_0) 11.5gb
 - [5.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/5_0) 14.0gb
-- [5.5bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/5_5) 
+- [5.5bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/5_5) 15.6gb
 - [6.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/6_0) 17.0gb
 - [7.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/7_0) 19.7gb
 - [8.0bpw](https://huggingface.co/machinez/Codestral-22B-v0.1-exl2/tree/8_0) 21.0gb
 
 # Model Card for Codestral-22B-v0.1
 
-Codestrall-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as Python, Java, C, C++, JavaScript, and Bash (more details in the [Blogpost](https://mistral.ai/news/codestral/)). The model can be queried:
+Codestral-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as Python, Java, C, C++, JavaScript, and Bash (more details in the [Blogpost](https://mistral.ai/news/codestral/)). The model can be queried:
 - As instruct, for instance to answer any questions about a code snippet (write documentation, explain, factorize) or to generate code following specific indications
 - As Fill in the Middle (FIM), to predict the middle tokens between a prefix and a suffix (very useful for software development add-ons like in VS Code)