Update app.py
Browse files
app.py
CHANGED
|
@@ -1,10 +1,8 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
from huggingface_hub import InferenceClient
|
|
|
|
| 3 |
|
| 4 |
-
""
|
| 5 |
-
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
|
| 6 |
-
"""
|
| 7 |
-
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
| 8 |
|
| 9 |
|
| 10 |
def respond(
|
|
@@ -45,7 +43,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
|
|
| 45 |
demo = gr.ChatInterface(
|
| 46 |
respond,
|
| 47 |
additional_inputs=[
|
| 48 |
-
gr.Textbox(value="
|
| 49 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
| 50 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
| 51 |
gr.Slider(
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
from huggingface_hub import InferenceClient
|
| 3 |
+
from transformers import AutoModel
|
| 4 |
|
| 5 |
+
model = AutoModel.from_pretrained("SchizoDev/Llama3-8b-CunnyGPT-16bit")
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
|
| 8 |
def respond(
|
|
|
|
| 43 |
demo = gr.ChatInterface(
|
| 44 |
respond,
|
| 45 |
additional_inputs=[
|
| 46 |
+
gr.Textbox(value="", label="System message"),
|
| 47 |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
| 48 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
| 49 |
gr.Slider(
|