File size: 2,976 Bytes
c4f5196 84f5648 5806ddb c4f5196 84f5648 c4f5196 baf09bc 5806ddb c5d71a6 5806ddb c8464bf 5806ddb 28490d7 53ba35d 28490d7 53ba35d 5806ddb 28490d7 53ba35d 28490d7 53ba35d baf09bc |
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 |
import gradio as gr
#import torch
import requests
import json
#from threading import Thread
#tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
#model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
#model = model.to('cuda:0')
#class StopOnTokens(StoppingCriteria):
# def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
# stop_ids = [29, 0]
# for stop_id in stop_ids:
# if input_ids[0][-1] == stop_id:
# return True
# return False
def predict(message, history):
history_transformer_format = history + [[message, ""]]
messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
for item in history_transformer_format])
#model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
#streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
#generate_kwargs = dict(
# model_inputs,
# streamer=streamer,
# max_new_tokens=1024,
# do_sample=True,
# top_p=0.95,
# top_k=1000,
# temperature=1.0,
# num_beams=1,
# stopping_criteria=StoppingCriteriaList([stop])
# )
#t = Thread(target=model.generate, kwargs=generate_kwargs)
#t.start()
#partial_message = ""
#for new_token in streamer:
# if new_token != '<':
# partial_message += new_token
# yield partial_message
# The URL for the API endpoint
url = "https://hook.us1.make.com/z7iqjks2oo1fa5u2ntqu4ggsnepdjhal"
# The header specifies that we're sending JSON data
headers = {
"Content-Type": "application/json"
}
# The data payload for the POST request
data = {
"parameters": {
"src_lang": "en_XX",
"tgt_lang": "fr_XX"
},
"inputs": message
}
# Make the POST request
response = requests.post(url, headers=headers, data=json.dumps(data), timeout=200)
# Check if the request was successful
if response.status_code == 200:
# Print the content of the response (the data the server returned)
response_json = response.json()
translation_item = response_json[0] if response_json else {}
print(response_json)
# Now use .get() to safely get the 'translation_text'
translation_text = translation_item.get('translation_text', 'No translation found.')
return translation_text
else:
# Print an error message if something went wrong
print(f"Request failed with status code {response.status_code}: {response.text}")
return "Sorry I could not answer your question as something went wrong"
return "Sorry I could not answer your question as something went wrong"
gr.ChatInterface(predict).launch() |