Svngoku commited on
Commit
9c9fd27
1 Parent(s): d672c23

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -0
README.md CHANGED
@@ -11,12 +11,35 @@ tags:
11
  base_model: unsloth/llama-3-8b-bnb-4bit
12
  ---
13
 
 
14
  # Uploaded model
15
 
16
  - **Developed by:** vutuka
17
  - **License:** apache-2.0
18
  - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
21
 
22
  [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
11
  base_model: unsloth/llama-3-8b-bnb-4bit
12
  ---
13
 
14
+
15
  # Uploaded model
16
 
17
  - **Developed by:** vutuka
18
  - **License:** apache-2.0
19
  - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
20
 
21
+ ## LLama CPP
22
+
23
+ ```py
24
+ from llama_cpp import Llama
25
+
26
+
27
+ llm = Llama.from_pretrained(
28
+ repo_id="vutuka/llama-3-8b-african-aya-f16",
29
+ filename="*F16.gguf",
30
+ verbose=False,
31
+ )
32
+
33
+ output = llm(
34
+ "Instruction: Ni nchi zipi zilizo tajiri zaidi duniani ?\n Response: ", # Prompt
35
+ max_tokens=None,
36
+ echo=True
37
+ )
38
+
39
+
40
+ print(output)
41
+ ```
42
+
43
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
44
 
45
  [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)