Update app.py

app.py

@@ -18,85 +18,85 @@ def extract_prediction(generated_text):
         extracted_content =  generated_text # generated_text.split("\[/INST\]")
     return extracted_content
 
-def NMRExtractor(Paragraph, max_length):
-    return 1,2,3,4,5,6,7
+# def NMRExtractor(Paragraph, max_length):
+#     return 1,2,3,4,5,6,7
 
 
-# def NMRExtractor(Paragraph, max_length):
-#     import torch
-#     import os
-#     import json
-#     import numpy as np
-#     # os.environ["CUDA_VISIBLE_DEVICES"] = "6"
-#     # # device = "cuda:0" if torch.cuda.is_available() else "cpu"
-#     device = "cpu"
-#     from transformers import  AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, HfArgumentParser, TrainingArguments, pipeline, logging
-#     # !pip install vllm
-#     # from vllm import LLM, SamplingParams
-#     # sampling_params = SamplingParams(temperature=0, top_p=1,max_tokens = 4096, stop = ['!!!'])
+def NMRExtractor(Paragraph, max_length):
+    import torch
+    import os
+    import json
+    import numpy as np
+    # os.environ["CUDA_VISIBLE_DEVICES"] = "6"
+    # # device = "cuda:0" if torch.cuda.is_available() else "cpu"
+    device = "cpu"
+    from transformers import  AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, HfArgumentParser, TrainingArguments, pipeline, logging
+    # !pip install vllm
+    # from vllm import LLM, SamplingParams
+    # sampling_params = SamplingParams(temperature=0, top_p=1,max_tokens = 4096, stop = ['!!!'])
     
-#     merged_dir = f"sweetssweets/NMRExtractor"
+    merged_dir = f"sweetssweets/NMRExtractor"
 
-#     # Reload model in FP16 and merge it with LoRA weights
-#     base_model = AutoModelForCausalLM.from_pretrained(
-#         merged_dir,
-#         low_cpu_mem_usage = True,
-#         return_dict = True,
-#         torch_dtype = torch.bfloat16,
-#         device_map = device,
-#         )
+    # Reload model in FP16 and merge it with LoRA weights
+    base_model = AutoModelForCausalLM.from_pretrained(
+        merged_dir,
+        low_cpu_mem_usage = True,
+        return_dict = True,
+        torch_dtype = torch.bfloat16,
+        device_map = device,
+        )
 
-#     # Reload tokenizer to save it
-#     tokenizer = AutoTokenizer.from_pretrained(merged_dir, trust_remote_code=True,truncation = True)
-#     tokenizer.pad_token = tokenizer.eos_token
-#     tokenizer.padding_side = "right"
+    # Reload tokenizer to save it
+    tokenizer = AutoTokenizer.from_pretrained(merged_dir, trust_remote_code=True,truncation = True)
+    tokenizer.pad_token = tokenizer.eos_token
+    tokenizer.padding_side = "right"
 
-#     #llm = LLM(model=merged_dir,device=device)
+    #llm = LLM(model=merged_dir,device=device)
 
-#     prom = '''Extract text containing 1H NMR and 13C NMR data, remove interference information such as reactants, raw materials, solvents and other non-final product names based on text semantics, and then extract the name, code or number of the final product. Please delete the IUPAC name Alias, numbers and ordinal numbers before and after fields, such as '2.1.3.', '(HL4)', '(9)', '(4d)'. NMR text should contain complete information, such as instrument power and solvent information, For example, "13C NMR text": "13C NMR (400 MHz, acetone-d6) 174.0 (C), 157.7 (C). Then split the NMR text. The content in NMR conditions is NMR instrument power and solvent information, such as "13C NMR conditions": "400MHz, acetone-d6". The content in the 13C NMR data removes information such as the position and shape of the peak,  such as "13C NMR data": "131.4–128.0, 157.7". The content in the 1H NMR data should include information such as the position and shape of the peak, such as "1H NMR data": "12.57 (s, 1H), 7.97–7.95 (d, J = 8.25 Hz, 2H)". Please keep the duplicate values of the original data and do not modify the number of decimal places. All responses must originate from information extracted from the given text, ensuring that the extracted content has not been modified or fragmented, and that capitalization and punctuation are exactly the same as the given text. Must end with {"IUPAC":"text","1H NMR text":"text","1H NMR conditions":"text","1H NMR data":"text","13C NMR text":"text","13C NMR conditions":"text","13C NMR data":"text"} format reply.'''
+    prom = '''Extract text containing 1H NMR and 13C NMR data, remove interference information such as reactants, raw materials, solvents and other non-final product names based on text semantics, and then extract the name, code or number of the final product. Please delete the IUPAC name Alias, numbers and ordinal numbers before and after fields, such as '2.1.3.', '(HL4)', '(9)', '(4d)'. NMR text should contain complete information, such as instrument power and solvent information, For example, "13C NMR text": "13C NMR (400 MHz, acetone-d6) 174.0 (C), 157.7 (C). Then split the NMR text. The content in NMR conditions is NMR instrument power and solvent information, such as "13C NMR conditions": "400MHz, acetone-d6". The content in the 13C NMR data removes information such as the position and shape of the peak,  such as "13C NMR data": "131.4–128.0, 157.7". The content in the 1H NMR data should include information such as the position and shape of the peak, such as "1H NMR data": "12.57 (s, 1H), 7.97–7.95 (d, J = 8.25 Hz, 2H)". Please keep the duplicate values of the original data and do not modify the number of decimal places. All responses must originate from information extracted from the given text, ensuring that the extracted content has not been modified or fragmented, and that capitalization and punctuation are exactly the same as the given text. Must end with {"IUPAC":"text","1H NMR text":"text","1H NMR conditions":"text","1H NMR data":"text","13C NMR text":"text","13C NMR conditions":"text","13C NMR data":"text"} format reply.'''
 
-#     #prompt = f"{prom} {Paragraph}"
-#     prompt = (f"<s>[INST] {prom} {Paragraph} [/INST]")
+    #prompt = f"{prom} {Paragraph}"
+    prompt = (f"<s>[INST] {prom} {Paragraph} [/INST]")
 
-#     import math
-#     import re
-#     # Generate texts from the prompts. The output is a list of RequestOutput objects
-#     # that contain the prompt, generated text, and other information.
+    import math
+    import re
+    # Generate texts from the prompts. The output is a list of RequestOutput objects
+    # that contain the prompt, generated text, and other information.
     
-#     pipe = pipeline(task="text-generation", model=base_model, tokenizer=tokenizer, max_length=max_length)
-#     print('prompt',prompt)
-#     result = pipe(f"{prompt}",max_length=max_length,truncation=True)
-#     print('result',result)
-#     generation = result[0]['generated_text']
-#     print('generation',generation) 
-#     generated_text = extract_prediction(generation)
-#     #output = llm.generate(prompt, sampling_params)
-#     print('generated_text',generated_text)
-#     #generated_text = output[0].outputs[0].text.strip()
+    pipe = pipeline(task="text-generation", model=base_model, tokenizer=tokenizer, max_length=max_length)
+    print('prompt',prompt)
+    result = pipe(f"{prompt}",max_length=512,truncation=True)
+    print('result',result)
+    generation = result[0]['generated_text']
+    print('generation',generation) 
+    generated_text = extract_prediction(generation)
+    #output = llm.generate(prompt, sampling_params)
+    print('generated_text',generated_text)
+    #generated_text = output[0].outputs[0].text.strip()
 
-#     #predictions_prob = math.exp(output[0].outputs[0].cumulative_logprob)
+    #predictions_prob = math.exp(output[0].outputs[0].cumulative_logprob)
     
-#     try:
-#         if generated_text is np.nan:
-#             return {}
-#         else:
-#             result = json.loads(str(generated_text).replace("'", "\""))
-#             print('@@@@@@@@@@@@@@@@@@@@@@@@@@@@')
-#             print(result.keys())
-#             return result['IUPAC'],result['1H NMR text'],result['1H NMR conditions'],result['1H NMR data'],result['13C NMR text'],result['13C NMR conditions'],result['13C NMR data']
-#     except (ValueError, TypeError, json.JSONDecodeError):
-#         print('####################################')
-#         pattern = r'"(IUPAC|1H NMR text|1H NMR conditions|1H NMR data|13C NMR text|13C NMR conditions|13C NMR data)":"(.*?)"'
-#         matches = re.findall(pattern, generated_text)
-#         result = {key: value for key, value in matches}
+    try:
+        if generated_text is np.nan:
+            return {}
+        else:
+            result = json.loads(str(generated_text).replace("'", "\""))
+            print('@@@@@@@@@@@@@@@@@@@@@@@@@@@@')
+            print(result.keys())
+            return result['IUPAC'],result['1H NMR text'],result['1H NMR conditions'],result['1H NMR data'],result['13C NMR text'],result['13C NMR conditions'],result['13C NMR data']
+    except (ValueError, TypeError, json.JSONDecodeError):
+        print('####################################')
+        pattern = r'"(IUPAC|1H NMR text|1H NMR conditions|1H NMR data|13C NMR text|13C NMR conditions|13C NMR data)":"(.*?)"'
+        matches = re.findall(pattern, generated_text)
+        result = {key: value for key, value in matches}
 
-#         keys = ["IUPAC", "1H NMR text", "1H NMR conditions", "1H NMR data", "13C NMR text", "13C NMR conditions", "13C NMR data"]
+        keys = ["IUPAC", "1H NMR text", "1H NMR conditions", "1H NMR data", "13C NMR text", "13C NMR conditions", "13C NMR data"]
 
-#         for key in keys:
-#             result[key] = result.get(key, 'N/A')
-#         print(result)
-#         return result['IUPAC'],result['1H NMR text'],result['1H NMR conditions'],result['1H NMR data'],result['13C NMR text'],result['13C NMR conditions'],result['13C NMR data']
-#     #return 1,2,3,4,5,6,7
+        for key in keys:
+            result[key] = result.get(key, 'N/A')
+        print(result)
+        return result['IUPAC'],result['1H NMR text'],result['1H NMR conditions'],result['1H NMR data'],result['13C NMR text'],result['13C NMR conditions'],result['13C NMR data']
+    #return 1,2,3,4,5,6,7
 demo = gr.Interface(
     fn=NMRExtractor,
     inputs=[gr.Textbox(label="Paragraph", lines=25,info='Paragraph'), gr.Slider(value=2048, minimum=2048, maximum=4096, step=1024),