Spaces:
Sleeping
Sleeping
File size: 1,933 Bytes
e82a10b 7cabdf8 c6e8f4b 62c5fe5 a07bb4e 12fb4a0 358c707 97a4aa1 12fb4a0 b5cd954 97a4aa1 ea06354 c7bde51 358c707 ea06354 12fb4a0 e560fe9 12fb4a0 7b17be9 12fb4a0 358c707 97a4aa1 12fb4a0 e560fe9 12fb4a0 f94f89d e6bccda |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
import gradio as gr
from huggingface_hub import InferenceClient
# Inference
model_text = "google/gemma-3-27b-it"
#model_text = "google/gemma-2-27b-it"
client = InferenceClient()
def fn_text(
prompt,
history,
input,
#system_prompt,
max_tokens,
temperature,
top_p,
):
#messages = [{"role": "system", "content": system_prompt}]
#history.append(messages[0])
#messages.append({"role": "user", "content": prompt})
#history.append(messages[1])
#messages = [{"role": "user", "content": prompt}]
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": prompt
},
{
"type": "image_url",
"image_url": {
"url": input
}
}
]
}
]
history.append(messages[0])
stream = client.chat.completions.create(
model = model_text,
messages = history,
max_tokens = max_tokens,
temperature = temperature,
top_p = top_p,
stream = True,
)
chunks = []
for chunk in stream:
chunks.append(chunk.choices[0].delta.content or "")
yield "".join(chunks)
app_text = gr.ChatInterface(
fn = fn_text,
type = "messages",
additional_inputs = [
gr.Textbox(label="Input"),
#gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-P"),
],
title = "Google Gemma",
description = model_text,
)
app = gr.TabbedInterface(
[app_text],
["Text"]
).launch() |