sourabhdattawad commited on
Commit
4242c49
1 Parent(s): 27d1090

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Usage
2
+
3
+ Package installation
4
+
5
+ ```
6
+ pip install llama-cpp-python "huggingface_hub[cli]"
7
+ ```
8
+
9
+ Download the model:
10
+
11
+ ```
12
+ huggingface-cli download sourabhdattawad/meta-llama-3-8b-instruct-gguf meta-llama-3-8b-instruct.Q8_0.gguf --local-dir . --local-dir-use-symlinks False
13
+ ```
14
+
15
+ ```Python
16
+ from llama_cpp import Llama
17
+ llm = Llama(
18
+ model_path="meta-llama-3-8b-instruct.Q8_0.gguf",
19
+ # n_gpu_layers=-1, # Uncomment to use GPU acceleration
20
+ # seed=1337, # Uncomment to set a specific seed
21
+ # n_ctx=2048, # Uncomment to increase the context window
22
+ )
23
+ output = llm(
24
+ "Q: Name the planets in the solar system? A: ", # Prompt
25
+ max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
26
+ stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
27
+ echo=True # Echo the prompt back in the output
28
+ )
29
+ ```