sekstini

sekstini

def solve(g, n=10**9):
    seq = [g]
    for i in range(n):
        if (g := cycle(g)) in seq:
            break
        seq.append(g)

    cycle_len = (i + 1) - (cycle_start := seq.index(g))
    final_index = cycle_start + (n - cycle_start) % cycle_len
    

sekstini

sekstini

sekstini

sekstini

Model,Output,Tokens,Cost ($),Latency (s),Speed (tokens/sec),Evaluation
OpenAIProvider('gpt-4-1106-preview'),"If you see the word 'push' in reverse through a glass door, it means you are looking at the text from the back side. The text is likely intended for people on the other side of the door, instructing them to push when they approach the door from that side.

Since you are seeing it in reverse, you are on the opposite side of the door from where the instruction applies. Therefore, you should do the opposite of what the reversed text says, which means you should pull the door to open it.",105,0.00257,2.75,38.18,3
OpenAIProvider('gpt-4-1106-preview'),"To solve the quadratic equation x^2 - 5x + 6 = 0, we can use factoring, the quadratic formula, or completing the square. The simplest method here is factoring because the equation is already in a form that suggests it might factor nicely.

We are looking for two numbers that multiply to give the constant term (6) and add up to give the coefficient of the x ter

sekstini

sekstini

sekstini

# Copyright 2022 EleutherAI and The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,

sekstini

# %%
import torch

# %%
# == Load 4bit weights and original weights ==
lin_4bit_dump = torch.load("lin_4bit_dump.pt", map_location="cuda")
lin_orig_weight = torch.load("lin_orig_weight.pt", map_location="cuda")

tmp = torch.load("input_and_outputs.pt", map_location="cuda")
x, output_4bit, output_orig = tmp["input"], tmp["output_4bit"], tmp["output_orig"]