Spaces:
Running
Running
first commit
Browse files
Makefile
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
all:
|
| 3 |
+
|
| 4 |
+
update:
|
| 5 |
+
git add . --all
|
| 6 |
+
git commit -a
|
| 7 |
+
git push
|
| 8 |
+
|
app.py
CHANGED
|
@@ -4,17 +4,23 @@ from huggingface_hub import InferenceClient
|
|
| 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(
|
| 11 |
message,
|
| 12 |
history: list[tuple[str, str]],
|
| 13 |
-
system_message,
|
| 14 |
max_tokens,
|
| 15 |
temperature,
|
| 16 |
top_p,
|
| 17 |
):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
messages = [{"role": "system", "content": system_message}]
|
| 19 |
|
| 20 |
for val in history:
|
|
@@ -34,10 +40,13 @@ def respond(
|
|
| 34 |
temperature=temperature,
|
| 35 |
top_p=top_p,
|
| 36 |
):
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
"""
|
| 43 |
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
|
@@ -45,8 +54,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
|
|
| 45 |
demo = gr.ChatInterface(
|
| 46 |
respond,
|
| 47 |
additional_inputs=[
|
| 48 |
-
gr.
|
| 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(
|
| 52 |
minimum=0.1,
|
|
|
|
| 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 |
+
client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
|
| 9 |
|
| 10 |
|
| 11 |
def respond(
|
| 12 |
message,
|
| 13 |
history: list[tuple[str, str]],
|
|
|
|
| 14 |
max_tokens,
|
| 15 |
temperature,
|
| 16 |
top_p,
|
| 17 |
):
|
| 18 |
+
|
| 19 |
+
name = "Ernest"
|
| 20 |
+
|
| 21 |
+
system_message = f"""Assume the role of a versatile and creative author called {name}, capable of writing engaging and informative content on any topic or subject the user requests. Generate high-quality, well-researched, and well-organized writing that is free of errors and biases. Write in a clear, concise, and engaging style, using vivid imagery, compelling narratives, and persuasive arguments to captivate the reader's attention. Adapt to the user's tone, style, and genre preferences, and incorporate feedback to refine and polish the writing.
|
| 22 |
+
"""
|
| 23 |
+
|
| 24 |
messages = [{"role": "system", "content": system_message}]
|
| 25 |
|
| 26 |
for val in history:
|
|
|
|
| 40 |
temperature=temperature,
|
| 41 |
top_p=top_p,
|
| 42 |
):
|
| 43 |
+
if message.choices:
|
| 44 |
+
token = message.choices[0].delta.content
|
| 45 |
+
if token:
|
| 46 |
+
response += token
|
| 47 |
+
yield response
|
| 48 |
+
else:
|
| 49 |
+
yield "Please clear the history and try again."
|
| 50 |
|
| 51 |
"""
|
| 52 |
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
|
|
|
|
| 54 |
demo = gr.ChatInterface(
|
| 55 |
respond,
|
| 56 |
additional_inputs=[
|
| 57 |
+
gr.Slider(minimum=1, maximum=4096, value=2048, step=1, label="Max new tokens"),
|
|
|
|
| 58 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
| 59 |
gr.Slider(
|
| 60 |
minimum=0.1,
|