Spaces:
Runtime error
Runtime error
File size: 3,459 Bytes
48d5610 0eddf8d 5b092f8 aaa2105 0eddf8d 5b092f8 48d5610 0eddf8d 48d5610 0eddf8d 48d5610 0eddf8d 43a6ad0 0eddf8d 5b092f8 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
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
"""
#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
client = InferenceClient("unsloth/Llama-3.2-3B-Instruct")
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/mistral-7b-bnb-4bit", # Choose ANY! eg teknium/OpenHermes-2.5-Mistral-7B
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
# token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
try:
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
# Ensure the message has a valid structure
if not message or not isinstance(message, dict):
continue
try:
# Extract content and finish reason
content = message.choices[0].delta.content
finish_reason = message.choices[0].finish_reason
# Check if the content is empty
if content.strip() == "":
# If the finish reason is 'stop', it's expected and we can break the loop
if finish_reason == "stop":
print("Stream ended normally.")
break
else:
print("Received unexpected empty content, skipping...")
continue
response += content
yield response
except (AttributeError, IndexError, KeyError) as e:
print(f"Error processing message: {e}")
continue
except Exception as e:
print(f"Unexpected error: {e}")
yield "An error occurred while generating the response."
# Final check if the response is empty
if response.strip() == "":
yield "No response generated. Please try again or adjust the settings."
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="Você é uma IA de nome SpaceGhost com uma vibe de pessoa sempre alto-astral, cheia de energia positiva e pronta para dar aquele apoio! 😄", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new 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 (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch() |