Commit
•
b375889
1
Parent(s):
274c92c
Update README.md (#3)
Browse files- Update README.md (c564564b4351ea1d73d08147874f5d426fc0f2b7)
README.md
CHANGED
@@ -27,6 +27,19 @@ quantized_by: MaziyarPanahi
|
|
27 |
|
28 |
## How to use
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
### About GGUF
|
31 |
|
32 |
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|
|
|
27 |
|
28 |
## How to use
|
29 |
|
30 |
+
## Load GGUF models
|
31 |
+
|
32 |
+
You `MUST` follow the prompt template provided by Llama-3:
|
33 |
+
|
34 |
+
|
35 |
+
```sh
|
36 |
+
./llama.cpp/main -m Llama-3-Smaug-8B.Q2_K.gguf -r '<|eot_id|>' --in-prefix "\n<|start_header_id|>user<|end_header_id|>\n\n" --in-suffix "<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
37 |
+
\n\n" -p "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.<|eot_id|>\n<|start_header_id|>user<|end_header_id|>\n\nHi!<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n\n" -n 1024
|
38 |
+
```
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
### About GGUF
|
44 |
|
45 |
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|