willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

vatsalsaglani

from typing import List, Dict, Literal, Union
from transformers import AutoTokenizer


class MistralAICtx:

    def __init__(self, model_name: str):
        assert "mistral" in model_name, "MistralCtx only available for Mistral models"
        self.tokenizer = AutoTokenizer.from_pretrained(
            "mistralai/Mistral-7B-Instruct-v0.2")

152334H

import torch
from unsloth import FastLlamaModel
from transformers import TrainingArguments
from datasets import load_dataset
from trl import DPOTrainer

model_name = "teknium/OpenHermes-2.5-Mistral-7B"
model_name = "./OpenHermes-2.5-Mistral-7B"
new_model = "NeuralHermes-2.5-Mistral-7B"

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

xenova

Birch-san

import torch
from typing import Optional
from flash_attn import flash_attn_func, flash_attn_qkvpacked_func
from diffusers.models.attention import Attention

class FlashAttnProcessor:
    r"""
    Processor for implementing memory efficient attention using flash_attn.
    """

CoffeeVampir3

import torch

from pipe import StableDiffusionXLPipelineNoWatermark
from pipei2i import StableDiffusionXLImg2ImgPipelineNoWatermark
from diffusers import DiffusionPipeline
from PIL import Image
import os
import gc
import pandas as pd
import random, sys

pacman100

import os
import sys
from typing import List

import fire
import torch
import transformers
from datasets import load_dataset, DatasetDict
from transformers import Seq2SeqTrainer, TrainerCallback, TrainingArguments, TrainerState, TrainerControl
from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR

0xabad1dea

Risk Assessment of GitHub Copilot

0xabad1dea, July 2021

this is a rough draft and may be updated with more examples

GitHub was kind enough to grant me swift access to the Copilot test phase despite me @'ing them several hundred times about ICE. I would like to examine it not in terms of productivity, but security. How risky is it to allow an AI to write some or all of your code?

Ultimately, a human being must take responsibility for every line of code that is committed. AI should not be used for "responsibility washing." However, Copilot is a tool, and workers need their tools to be reliable. A carpenter doesn't have to

dataplayer12

add_executable(infervideo infervideo.cpp)
target_link_libraries(infervideo PRIVATE retinanet ${OpenCV_LIBS} cuda ${CUDA_LIBRARIES})