Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,8 @@ datasets:
|
|
| 29 |
This model was created by [jphme](https://huggingface.co/jphme) and is a finetune of Meta's [Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat).
|
| 30 |
This repository contains the model [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) in GGUF format.
|
| 31 |
|
| 32 |
-
##
|
|
|
|
| 33 |
```
|
| 34 |
# Convert original model to FP16 GGUF format
|
| 35 |
python3 llama.cpp/convert.py ./original-models/Llama-2-13b-chat-german --outtype f16 --outfile ./converted_gguf/Llama-2-13b-chat-german-GGUF.fp16.bin
|
|
|
|
| 29 |
This model was created by [jphme](https://huggingface.co/jphme) and is a finetune of Meta's [Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat).
|
| 30 |
This repository contains the model [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) in GGUF format.
|
| 31 |
|
| 32 |
+
## Replication Steps
|
| 33 |
+
Clone llama.cpp *(Commit: 9e20231)*, compile it 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.
|
| 34 |
```
|
| 35 |
# Convert original model to FP16 GGUF format
|
| 36 |
python3 llama.cpp/convert.py ./original-models/Llama-2-13b-chat-german --outtype f16 --outfile ./converted_gguf/Llama-2-13b-chat-german-GGUF.fp16.bin
|