Upload app.py
#2
by
awinml
- opened
app.py
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from llama_cpp import Llama
|
3 |
+
|
4 |
+
llm = Llama(model_path="vicuna-AlekseyKorshuk-7B-GPTQ-4bit-128g.GGML.bin", n_ctx=2048)
|
5 |
+
|
6 |
+
def generate_text(llm, prompt, max_tokens=468, temperature=0.1, top_p=0.5):
|
7 |
+
output = llm(prompt, max_tokens=max_tokens, temperature=temperature, top_p=top_p, echo=False, stop=["#"])
|
8 |
+
text = output['choices'][0]['text']
|
9 |
+
return text
|
10 |
+
|
11 |
+
input_text = gr.inputs.Textbox(lines= 10, label="Enter your input text")
|
12 |
+
output_text = gr.outputs.Textbox(label="Output text")
|
13 |
+
|
14 |
+
description = "llama.cpp implementation in python [https://github.com/abetlen/llama-cpp-python]"
|
15 |
+
|
16 |
+
examples = [
|
17 |
+
["What is the capital of France? ", "The capital of France is Paris."],
|
18 |
+
["Who wrote the novel 'Pride and Prejudice'?", "The novel 'Pride and Prejudice' was written by Jane Austen."],
|
19 |
+
["What is the square root of 64?", "The square root of 64 is 8."]
|
20 |
+
]
|
21 |
+
|
22 |
+
gr.Interface(fn=generate_text, inputs=input_text, outputs=output_text, title="Vicuna Language Model", description=description, examples=examples).launch()
|
23 |
+
|