data2json

#!/usr/bin/env python3
"""
Complete training pipeline for Qwen3-4B with Super Weight Preservation
Supports HuggingFace datasets with automatic chat template conversion
"""

import torch
import torch.nn as nn
from torch.utils.data import DataLoader, Dataset
import json

data2json

import torch
from transformers import AutoModelForCausalLM

# Load models
llama3_base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")
llama3_inst = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
llama31_base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B")

# Calculate Δθ = θpost - θbase
delta_params = {}

data2json

import argparse
from typing import List, Dict, Any, Optional
from vllm import EngineArgs, LLMEngine, RequestOutput, SamplingParams
from datasets import load_dataset
from tqdm import tqdm
import json
import re
from dataclasses import dataclass
from vllm.utils import FlexibleArgumentParser

data2json

import re
import torch
import numpy as np
from datasets import Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

class SimpleCalculator:
    """Simple calculator tool implementation"""

data2json

# train_grpo.py
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

# Load and prep dataset

data2json

import asyncio
import os
import json
from openai import AsyncOpenAI
from datetime import datetime
import random

# Set up the client with custom base URL
client = AsyncOpenAI(base_url="http://0.0.0.0:8000/v1/")

data2json

essobi@thegreenbox:~/LLaMA-Factory$ more OKG.py
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
checkpoint = "meta-llama/Meta-Llama-3.1-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(
    checkpoint, torch_dtype=torch.bfloat16, device_map="auto"
)

data2json

curl -X POST http://192.168.50.146:8000/v1/chat/completions \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
  "messages": [
    {
      "content": "You are a helpful assistant that can check the weather. Use the get_weather tool when asked about weather conditions. If you choose to call a function ONLY reply in the following format: <{sta
rt_tag}={function_name}>{parameters}{end_tag} where start_tag => <function parameters => a JSON dict with the function argument name as key and function argument value as value. end_tag => </function>",
      "role": "system"

data2json

curl -s -X POST 'http://0.0.0.0:8000/v1/chat/completions' -H "Content-Type: application/json" -d '{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "system",
      "content": "Environment: ipython\nTools: brave_search, wolfram_alpha\n\nCutting Knowledge Date: December 2023\nToday Date: 23 Jul 2024\n\nYou are a helpful Assistant."
    },
    {
      "role": "user",
      "content": "Can you help me solve this equation: x^3 - 4x^2 + 6x - 24 = 0"

data2json

#!/usr/bin/env python
#  t - The missing LLM token counting and splitting tool for UNIX

import argparse
import sys
from typing import Optional, List
import math
import os

import tiktoken