Spaces:
Sleeping
Sleeping
File size: 3,652 Bytes
e82a10b 7cabdf8 a07bb4e 12fb4a0 0b95001 399bbc5 0b95001 bf50cbd 12fb4a0 97a4aa1 12fb4a0 b5cd954 0b95001 97a4aa1 ea06354 12fb4a0 399bbc5 bf50cbd 399bbc5 bf50cbd 12fb4a0 399bbc5 12fb4a0 7b17be9 12fb4a0 399bbc5 12fb4a0 399bbc5 97a4aa1 12fb4a0 399bbc5 e560fe9 12fb4a0 399bbc5 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 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient()
# Gemma 2
model_gemma_2 = "google/gemma-2-27b-it"
def fn_gemma_2(
prompt,
history,
#system_prompt,
max_tokens,
temperature,
top_p,
):
# Without System Prompt
messages = [{"role": "user", "content": prompt}]
history.append(messages[0])
# With System Prompt
#messages = [{"role": "system", "content": system_prompt}]
#history.append(messages[0])
#messages.append({"role": "user", "content": prompt})
#history.append(messages[1])
stream = client.chat.completions.create(
model = model_gemma_2,
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_gemma_2 = gr.ChatInterface(
fn = fn_gemma_2,
type = "messages",
additional_inputs = [
#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 2",
description = model_gemma_2,
)
# Gemma 3
model_gemma_3 = "google/gemma-3-27b-it"
def fn_gemma_3(
prompt,
history,
input,
#system_prompt,
max_tokens,
temperature,
top_p,
):
# Without System Prompt
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": prompt
},
{
"type": "image_url",
"image_url": {
"url": input
}
}
]
}
]
history.append(messages[0])
# With System Prompt
#messages = [{"role": "system", "content": system_prompt}]
#history.append(messages[0])
#messages.append([
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": prompt
# },
# {
# "type": "image_url",
# "image_url": {
# "url": input
# }
# }
# ]
# }
#])
#history.append(messages[1])
stream = client.chat.completions.create(
model = model_gemma_3,
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_gemma_3 = gr.ChatInterface(
fn = fn_gemma_3,
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 3",
description = model_gemma_3,
)
app = gr.TabbedInterface(
[app_gemma_2, app_gemma_3],
["Gemma 2", "Gemma 3"]
).launch() |