freefallr commited on
Commit
ea18b32
·
1 Parent(s): 652e73c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -20,12 +20,15 @@ This repository contains the model [jphme/Llama-2-13b-chat-german](https://huggi
20
  The original model was created by [jphme](https://huggingface.co/jphme) and is a fine-tune of [Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) from Meta, trained on German instructions.
21
 
22
  ## Model Profile
23
- The Model Profile describes all relevant properties of the AI model in a digestible and easy-to-read way.
 
24
 
25
  |Property|Details|
26
  |----------------------------|--------------------------------------------------------------------------------------------------------------|
27
  | **Model** | [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) |
28
  | **Type** | Text Generation |
 
 
29
  | **File Format** | GGUF |
30
  | **Quantization Types** | 8 Bit <br>5 Bit (K_M) |
31
  | **Tools used** | llama.cpp (Commit 9e20231) |
 
20
  The original model was created by [jphme](https://huggingface.co/jphme) and is a fine-tune of [Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) from Meta, trained on German instructions.
21
 
22
  ## Model Profile
23
+ The Model Profile describes relevant properties of the model in a standardized, digestible and easy-to-read way.
24
+ It uses the Unified AI Description Format (.aidf), which is a novel format with the aim to standardize property and metadata descriptions of AI models.
25
 
26
  |Property|Details|
27
  |----------------------------|--------------------------------------------------------------------------------------------------------------|
28
  | **Model** | [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) |
29
  | **Type** | Text Generation |
30
+ | **Finetuned for** | Chat | |
31
+ | **Architecture** | Transformers |
32
  | **File Format** | GGUF |
33
  | **Quantization Types** | 8 Bit <br>5 Bit (K_M) |
34
  | **Tools used** | llama.cpp (Commit 9e20231) |