shahules786

nli_prompt = RagasPrompt(
    instruction="""Natural language inference. Use only "Yes" (1) or "No" (0) as a binary verdict.""",
    examples=[
        {
            "Context":"""John is a student at XYZ University. He is pursuing a degree in Computer Science. He is enrolled in several courses this semester, including Data Structures, Algorithms, and Database Management. John is a diligent student and spends a significant amount of time studying and completing assignments. He often stays late in the library to work on his projects.
                        statement_1: John is majoring in Biology.
                        statement_2: John is taking a course on Artificial Intelligence. 
                        statement_3: John is a dedicated student. 
                        statement_4: John has a part-time job.""",
            "Answer":"""[

shahules786

from ragas import evaluate
from datasets import Dataset
import os

os.environ["OPENAI_API_KEY"] = "your-openai-key"

# prepare your huggingface dataset in the format
# Dataset({
#     features: ['question','contexts','answer'],

shahules786

{"input": [{"role": "system", "content": "Complete the phrase as concisely as possible."}, 
{"role": "user", "content": "ABC AI is a company specializing in ML "}], "ideal": "observability"}

shahules786

from huggingface_hub import HfApi
import os
import argparse

api = HfApi()

model_files = ["tokenizer.json","special_tokens_map.json","tokenizer_config.json","config.json","pytorch_model.bin"]


if __name__ == "__main__":

shahules786

@dataclass
class RMDataCollator:
    tokenizer: PreTrainedTokenizer
    max_length: int = 512

    def format_example(self, example, eos, prompt=False):
        sp_token = SPECIAL_TOKENS["prompter"] if prompt else SPECIAL_TOKENS["assistant"]
        return "{}{}{}".format(sp_token, example, eos)

    def process_example(self, example):

shahules786

class WebGPT:
    name = "openai/webgpt_comparisons"

    def __init__(self, split: str = "train"):
        super().__init__()
        self.split = split
        dataset = load_dataset(self.name, split=self.split)
        self.dataset_dict = defaultdict(dict)
        for item in dataset:

shahules786

class RMLoss(nn.Module):
    """ """

    def __init__(
        self,
        reduction=None,
        beta=0.001,
    ):
        super().__init__()
        self.reduction = reduction

shahules786

@dataclass
class GPTNeoxRMOuptput(ModelOutput):
    """
    Reward Model Output
    """

    logits: torch.FloatTensor = None


class GPTNeoXRM(GPTNeoXPreTrainedModel):

shahules786

def reintialize(model,num_layers):

        """reinitialize models weights untill num_layers starting from bottom layer"""


        return model


model = DefinedModel()
model = reinitialize(model,2)

shahules786

def llrd(model,peak_lr,multiplicative factor):

        """sets learning rate for each layer and returns the parameters"""

        parameters = get_model_parameters()


        return parameters