This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| const std = @import("std"); | |
| const assert = std.debug.assert; | |
| const Allocator = std.mem.Allocator; | |
| const Io = std.Io; | |
| pub fn main() !void { | |
| var debug_allocator: std.heap.DebugAllocator(.{}) = .init; | |
| const gpa = debug_allocator.allocator(); | |
| //const gpa = std.heap.smp_allocator; |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # 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 |