dosubot[bot]
commented
12 months ago 🤖
Hello,
The error you're encountering is due to the way you're initializing the LLMChain. The llm and prompt parameters are expected to be instances of BaseLanguageModel and BasePromptTemplate respectively, not dictionaries.
Here's how you can correctly initialize the LLMChain:
from langchain.prompt_templates import TextPromptTemplate
from langchain.language_models import HuggingFaceLanguageModel
# Define your prompt template
prompt_template = TextPromptTemplate(
prompt="Summarize this text: {text}",
input_variables=["text"],
)
# Define your language model
language_model = HuggingFaceLanguageModel(
model_name="Sanjay1234/Trillo-Project",
)
# Initialize the LLMChain
llm_chain = LLMChain(
llm=language_model,
prompt=prompt_template,
)In this example, TextPromptTemplate is used for the prompt, and HuggingFaceLanguageModel is used for the language model. You can replace these with your own implementations if you have them, as long as they inherit from BasePromptTemplate and BaseLanguageModel respectively.
Please try this and let me know if you encounter any further issues.
Sources
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
SanjayDevarajan03
Issue you'd like to raise.
The code for my model for sentiment analysis (this works, the problem is in the next part of my code)
from datasets import load_dataset,Dataset from sentence_transformers.losses import CosineSimilarityLoss from setfit import SetFitModel, SetFitTrainer, sample_dataset from transformers import pipeline import pandas as pd import langchain
df = pd.read_csv("C:/Users/sanja/OneDrive/Desktop/Trillo InternShip/train.csv",encoding='ISO-8859-1')
df = pd.read_csv("C:/Users/sanja/OneDrive/Desktop/Trillo InternShip/train-utf-8.csv")
Create a mapping from string labels to integer labels
label_mapping = {"negative": 0, "neutral": 1, "positive": 2} # Customize this mapping as needed
Apply the mapping to the "sentiment" column
df['label'] = df['label'].map(label_mapping)
Specify the columns for text (input) and label (output)
text_column = "selected_text" label_column = "label"
Assuming you have already preprocessed and tokenized your text data
dataset = Dataset.from_pandas(df)
num_samples_per_class = 8
Simulate the few-shot regime by sampling 8 examples per class
train_dataset = sample_dataset(dataset, label_column=label_column, num_samples=num_samples_per_class) eval_dataset = dataset # Assuming you want to evaluate on the same DataFrame
Load a SetFit model from Hub
model = SetFitModel.from_pretrained("sentence-transformers/paraphrase-mpnet-base-v2")
Create trainer
trainer1 = SetFitTrainer( model=model, train_dataset=train_dataset, eval_dataset=eval_dataset, loss_class=CosineSimilarityLoss, metric="accuracy", batch_size=16, num_iterations=20, # The number of text pairs to generate for contrastive learning num_epochs=1, # The number of epochs to use for contrastive learning column_mapping={text_column: "text", label_column: "label"} # Map dataset columns to text/label expected by trainer )
Train and evaluate
trainer1.train() metrics = trainer1.evaluate()
Pushing model to hub
trainer1.push_to_hub("Sanjay1234/Trillo-Project")
But here I get a problem when I do transformation,
from langchain.chains import TransformChain, LLMChain, SimpleSequentialChain from sentence_transformers.losses import CosineSimilarityLoss from setfit import SetFitModel, SetFitTrainer, sample_dataset from transformers import pipeline
def transform_func(text): shortened_text = "\n\n".join(text.split("\n\n")[:3]) return shortened_text
transform_chain = TransformChain( input_variables=["text"], output_variables=["output_text"], transform=transform_func )
I get a problem here
llm_chain = LLMChain( llm={"llm": "Sanjay1234/Trillo-Project"}, # Provide the llm parameter as a dictionary prompt={"prompt": "Summarize this text:"} )
sequential_chain = SimpleSequentialChain(chains=[transform_chain, llm_chain]) text = "This is a long text. I want to transform it to only the first 3 paragraphs." transformed_text = sequential_chain.run(text) print(transformed_text)
I get the following error.-
ValidationError Traceback (most recent call last) Cell In[26], line 1 ----> 1 llm_chain = LLMChain( 2 llm={"llm": "Sanjay1234/Trillo-Project"}, # Provide the llm parameter as a dictionary 3 prompt={"prompt": "Summarize this text:"} 4 )
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\langchain\load\serializable.py:74, in Serializable.init(self, kwargs) 73 def init(self, kwargs: Any) -> None: ---> 74 super().init(**kwargs) 75 self._lc_kwargs = kwargs
File ~\AppData\Local\Programs\Python\Python39\lib\site-packages\pydantic\main.py:341, in pydantic.main.BaseModel.init()
ValidationError: 2 validation errors for LLMChain prompt Can't instantiate abstract class BasePromptTemplate with abstract methods format, format_prompt (type=type_error) llm Can't instantiate abstract class BaseLanguageModel with abstract methods agenerate_prompt, apredict, apredict_messages, generate_prompt, invoke, predict, predict_messages (type=type_error)
Suggestion:
No response