Spaces:
Runtime error
Runtime error
File size: 3,980 Bytes
37cccbf |
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 |
import spaces
#######################
'''
Name: Phine Inference
License: MIT
'''
#######################
##### Dependencies
""" IMPORTANT: Uncomment the following line if you are in a Colab/Notebook environment """
#!pip install gradio einops accelerate bitsandbytes transformers
#####
import gradio as gr
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import random
import re
def cut_text_after_last_token(text, token):
last_occurrence = text.rfind(token)
if last_occurrence != -1:
result = text[last_occurrence + len(token):].strip()
return result
else:
return None
class _SentinelTokenStoppingCriteria(transformers.StoppingCriteria):
def __init__(self, sentinel_token_ids: torch.LongTensor,
starting_idx: int):
transformers.StoppingCriteria.__init__(self)
self.sentinel_token_ids = sentinel_token_ids
self.starting_idx = starting_idx
def __call__(self, input_ids: torch.LongTensor,
_scores: torch.FloatTensor) -> bool:
for sample in input_ids:
trimmed_sample = sample[self.starting_idx:]
if trimmed_sample.shape[-1] < self.sentinel_token_ids.shape[-1]:
continue
for window in trimmed_sample.unfold(
0, self.sentinel_token_ids.shape[-1], 1):
if torch.all(torch.eq(self.sentinel_token_ids, window)):
return True
return False
model_path = 'freecs/phine-2-v0'
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, load_in_4bit=False, torch_dtype=torch.float16).to(device) #remove .to() if load_in_4/8bit = True
sys_message = "You are an AI assistant named Phine developed by FreeCS.org. You are polite and smart." #System Message
@spaces.GPU
def phine(message, history, temperature, top_p, top_k, repetition_penalty):
n = 0
context = ""
if history and len(history) > 0:
for x in history:
for h in x:
if n%2 == 0:
context+=f"""\n<|prompt|>{h}\n"""
else:
context+=f"""<|response|>{h}"""
n+=1
else:
context = ""
prompt = f"""\n<|system|>{sys_message}"""+context+"\n<|prompt|>"+message+"<|endoftext|>\n<|response|>"
tokenized = tokenizer(prompt, return_tensors="pt").to(device)
stopping_criteria_list = transformers.StoppingCriteriaList([
_SentinelTokenStoppingCriteria(
sentinel_token_ids=tokenizer(
"<|endoftext|>",
add_special_tokens=False,
return_tensors="pt",
).input_ids.to(device),
starting_idx=tokenized.input_ids.shape[-1])
])
token = model.generate(**tokenized,
stopping_criteria=stopping_criteria_list,
do_sample=True,
max_length=2048, temperature=temperature, top_p=top_p, top_k = top_k, repetition_penalty = repetition_penalty
)
completion = tokenizer.decode(token[0], skip_special_tokens=False)
token = "<|response|>"
res = cut_text_after_last_token(completion, token)
return res.replace('<|endoftext|>', '')
demo = gr.ChatInterface(phine,
additional_inputs=[
gr.Slider(0.1, 2.0, label="temperature", value=0.5),
gr.Slider(0.1, 2.0, label="Top P", value=0.9),
gr.Slider(1, 500, label="Top K", value=50),
gr.Slider(0.1, 2.0, label="Repetition Penalty", value=1.15)
]
)
if __name__ == "__main__":
demo.queue().launch(share=True, debug=True) #If debug=True causes problems you can set it to False
|