morgendigital
/

Llama-2-13b-chat-german-GGUF

Text Generation

Model card Files Files and versions Community

freefallr commited on Sep 5, 2023

Commit

534e719

·

1 Parent(s): 528232f

Update README.md

Files changed (1) hide show

README.md +5 -6

README.md CHANGED Viewed

@@ -21,15 +21,14 @@ The original model was created by [jphme](https://huggingface.co/jphme) and is a
 ## Model Profile
-|               |                                                                                              |
 |----------------------------|--------------------------------------------------------------------------------------------------------------|
 | **Model**                  | [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german)                        |
 | **Format**                 | GGUF                                                                                                         |
-| **Quantization Levels**    | 8 Bit<br> 5 Bit K_M                                                                                          |
-| **Conversion Tool used**   | llama.cpp (Commit: 9e20231)                                                                                  |
-| **Original Model Creator** | [jphme](https://huggingface.co/jphme)                                                                      |
-| **Training Data Info**     | Prorietary German Conversation Dataset, German SQuAD, German legal SQuAD data, augmented with "wrong" contexts, to improve factual RAG |
 ## Replication Steps
 Clone and install llama.cpp *(Commit: 9e20231)* and use the provided `convert.py` file to convert the original model to GGUF with FP16 precision. The converted model will then be used to do further quantization.

 ## Model Profile
+The model profile describes the properties
 |----------------------------|--------------------------------------------------------------------------------------------------------------|
 | **Model**                  | [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german)                        |
 | **Format**                 | GGUF                                                                                                         |
+| **Quantization Types**     | - 8 Bit <br>- 5 Bit K_M                                                                                          |
+| **Conversion Tool**        | llama.cpp (Commit: 9e20231)                                                                                  |
+| **Original Model Creator** | [jphme](https://huggingface.co/jphme)                                                                        |
+| **Training Data**          | Prorietary German Conversation Dataset, German SQuAD, German legal SQuAD data, augmented with "wrong" contexts, to improve factual RAG |
 ## Replication Steps
 Clone and install llama.cpp *(Commit: 9e20231)* and use the provided `convert.py` file to convert the original model to GGUF with FP16 precision. The converted model will then be used to do further quantization.