System Info

Kaggle script running GPT:oss20b that worked this morning (pulls transformers from GitHub) has just started giving this error:

'GptOssConfig' object has no attribute 'max_position_embeddings

Not a big user and it's a plug and play script so can't elaborate much, sorry.

Here's the env!

Copy-and-paste the text below in your GitHub issue and FILL OUT the two last points.

• transformers version: 4.56.0.dev0
• Platform: Linux-6.6.56+-x86_64-with-glibc2.35
• Python version: 3.11.13
• Huggingface_hub version: 0.34.4
• Safetensors version: 0.5.3
• Accelerate version: 1.8.1
• Accelerate config: not found
• DeepSpeed version: not installed
• PyTorch version (accelerator?): 2.8.0+cu128 (CUDA)
• Tensorflow version (GPU?): 2.18.0 (True)
• Flax version (CPU?/GPU?/TPU?): 0.10.6 (gpu)
• Jax version: 0.5.2
• JaxLib version: 0.5.1
• Using distributed or parallel set-up in script?: Yes
• Using GPU in script?: Yes
• GPU type: Tesla T4

Who can help?

@ArthurZucker

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

Load model & tokenizer (keep it simple for now)

tokenizer = AutoTokenizer.from_pretrained(model_id, device_map="auto")
model = AutoModelForCausalLM.from_pretrained(model_id,device_map="auto")

Expected behavior

Script ran w/o errors this morning, powers multiple notebooks.