vgel

# /// script
# dependencies = [ "transformers", "accelerate" ]
# ///

# run on 2xH200 rented from primeintellect.ai

import gc

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

toy-crane

# Frontend Design Guideline

This document summarizes key frontend design principles and rules, showcasing
recommended patterns. Follow these guidelines when writing frontend code.

# Readability

Improving the clarity and ease of understanding code.

AstraBert

nrbnlulu

from datetime import datetime
import json
import re
import timeit
from contextlib import contextmanager
from dataclasses import dataclass
from typing import Annotated, Any, Callable, Iterator, TypedDict
from pydantic.annotated_handlers import GetJsonSchemaHandler

tsensei

import "dotenv/config";
import { OpenAIEmbeddings } from "@langchain/openai";
import { TextLoader } from "langchain/document_loaders/fs/text";
import natural from "natural";
import * as math from "mathjs";
import { quantile } from "d3-array";

interface SentenceObject {
  sentence: string;
  index: number;

densumesh

  pub fn get_splade_vector(
        input: String,
        model: Model,
        tokenizer: &Tokenizer,
    ) -> Result<Vec<f32>, ServiceError> {
        let tokenized_inputs = tokenizer.encode(input, false).unwrap();
        let tokens = tokenized_inputs.get_ids().to_vec();
        let token_ids = Tensor::new(tokens.as_slice(), &candle_core::Device::Cpu)
            .map_err(|e| ServiceError::BadRequest(format!("Could not create tensor: {}", e)))?;

mlabonne

# Based on younesbelkada/finetune_llama_v2.py
# Install the following libraries:
# pip install accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7 scipy

from dataclasses import dataclass, field
from typing import Optional

import torch
from datasets import load_dataset
from transformers import (

MihailCosmin

#!/bin/bash

### steps ####
# verify the system has a cuda-capable gpu
# download and install the nvidia cuda toolkit and cudnn
# setup environmental variables
# verify the installation
###

### to verify your gpu is cuda enable check

nreimers

# 1) Install dependencies: pip install cohere datasets elasticsearch==8.6.2
# 2) Start a local Elasticsearch server: docker run -p 9200:9200 -p 9300:9300 -e "discovery.type=single-node" elasticsearch:8.6.2
# 3) Get your Cohere API key and past it below

from elasticsearch import Elasticsearch, helpers
import cohere
from datasets import load_dataset


# Get your cohere API key on: www.cohere.com

edp1096

스탠포드알파카 학습하기

• runpod.io에서 실행
• Llama-7B 사용
• llama 모델을 workspace 밖 홈디렉에서 다운받기 때문에 컨테이너 용량을 15GB 정도 잡아줘야 한다
• Volume 용량은 30G 이상으로 잡아줘야 한다 - 파인튜닝 끝나고 output에 저장되는 파일들이 25GB 남짓되는 크기가 필요하기 때문
• 허깅페이스 모델은 별도 다운 받을 필요 없고
• A100 80G X 4로 처음 시작 1% 지점에서 예상시간 5:37:57 찍힘

Install vi