Spaces:
Runtime error
Runtime error
File size: 4,343 Bytes
be1ce55 cf51cda be1ce55 fd70c4a 3dd2b2b fd70c4a 3dd2b2b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
'''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")
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 = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
"""
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="You are a friendly Chatbot.", 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()'''
#!pip install -U "transformers==4.40.0" --upgrade
#!pip install -i https://pypi.org/simple/ bitsandbytes
#!pip install accelerate
import transformers
import torch
model_id = "unsloth/llama-3-8b-Instruct-bnb-4bit"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={
"torch_dtype": torch.float16,
"quantization_config": {"load_in_4bit": True},
"low_cpu_mem_usage": True,
},
)
messages = [
{"role" : "system",
"content": "You are an interviewer testing the user whether he can be a good manager or not. When the user says hi there!, i want you to begin"},
{"role" : "user",
"content": """hi there!"""},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
#!pip install gradio
import gradio as gr
messages = [{"role" : "system",
"content": "You are an interviewer testing the user whether he can be a good manager or not. When the user says hi there!, i want you to begin"},
{"role" : "user",
"content": """hi there!"""},]
def add_text(history, text):
global messages #message[list] is defined globally
history = history + [(text,'')]
messages = messages + [{"role":'user', 'content': text}]
return history, ''
def generate(history):
global messages
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response_msg = outputs[0]["generated_text"][len(prompt):]
for char in response_msg:
history[-1][1] += char
yield history
pass
with gr.Blocks() as demo:
chatbot = gr.Chatbot(value=[], elem_id="chatbot")
with gr.Row():
txt = gr.Textbox(
show_label=False,
placeholder="Enter text and press enter",
)
txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(
generate, inputs =[chatbot,],outputs = chatbot,)
demo.queue()
demo.launch(debug=True) |