GPT-oss-YearWise

This repository contains the checkpoint-5500 model checkpoint from the YearWise training run.

Model Details

• Repository: StarLiu714/GPT-oss-YearWise
• Branch: main
• Checkpoint source: /Users/starliu/Downloads/train_full-0609/checkpoint-5500/
• Primary weights: model.safetensors
• License: MIT

Files

The checkpoint includes model weights, tokenizer assets, chat template, optimizer state, scheduler state, RNG state, trainer state, and training arguments.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "StarLiu714/GPT-oss-YearWise"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="auto")

Training and Evaluation

This model card documents the uploaded checkpoint and license. Detailed dataset composition, training configuration, and evaluation metrics should be interpreted from the accompanying training artifacts in this repository where applicable.

License

This model is released under the MIT License.