타임아웃 문제

타임아웃 에러 때문에 마지막 실습이 어렵습니다.
==((====))== Unsloth 2026.1.2: Fast Llama patching. Transformers: 4.57.3. \\ /| Tesla T4. Num GPUs = 1. Max memory: 14.741 GB. Platform: Linux. O^O/ \_/ \ Torch: 2.9.0+cu126. CUDA: 7.5. CUDA Toolkit: 12.6. Triton: 3.5.0 \ / Bfloat16 = FALSE. FA [Xformers = None. FA2 = False] "-____-" Free license: http://github.com/unslothai/unsloth Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!

---------------------------------------------------------------------------

TimeoutError                              Traceback (most recent call last)

/usr/local/lib/python3.12/dist-packages/unsloth/models/_utils.py in _get_statistics(statistics, force_download)
   1173             try:
-> 1174                 time_limited_stats_check()
   1175             except TimeoutError:

6 frames

/usr/local/lib/python3.12/dist-packages/unsloth_zoo/rl_environments.py in wrapper(*args, **kwargs)
    774             elif effective_backend == "process":
--> 775                 return _run_in_subprocess(func, seconds, args, kwargs,
    776                                           start_method=start_method, kill_grace=kill_grace)

/usr/local/lib/python3.12/dist-packages/unsloth_zoo/rl_environments.py in _run_in_subprocess(func, seconds, args, kwargs, start_method, kill_grace)
    701                     proc.join()
--> 702             raise TimeoutError(f"Timed out after {seconds:g}s")
    703     except KeyboardInterrupt:

TimeoutError: Timed out after 120s

During handling of the above exception, another exception occurred:

TimeoutError                              Traceback (most recent call last)

/tmp/ipython-input-2933263888.py in <cell line: 0>()
      4 
      5 # ✅ STEP 1: 모델 및 토크나이저 로딩 (Unsloth LLaMA 3.1 8B 기준)
----> 6 model, tokenizer = FastLanguageModel.from_pretrained(
      7     model_name = "unsloth/Meta-Llama-3.1-8B",
      8     max_seq_length = 2048,

/usr/local/lib/python3.12/dist-packages/unsloth/models/loader.py in from_pretrained(model_name, max_seq_length, dtype, load_in_4bit, load_in_8bit, load_in_16bit, full_finetuning, token, device_map, rope_scaling, fix_tokenizer, trust_remote_code, use_gradient_checkpointing, resize_model_vocab, revision, use_exact_model_name, offload_embedding, float32_mixed_precision, fast_inference, gpu_memory_utilization, float8_kv_cache, random_state, max_lora_rank, disable_log_stats, qat_scheme, load_in_fp8, unsloth_tiled_mlp, *args, **kwargs)
    582             load_in_8bit_kwargs = False
    583 
--> 584         model, tokenizer = dispatch_model.from_pretrained(
    585             model_name = model_name,
    586             max_seq_length = max_seq_length,

/usr/local/lib/python3.12/dist-packages/unsloth/models/llama.py in from_pretrained(model_name, max_seq_length, dtype, load_in_4bit, token, device_map, rope_scaling, fix_tokenizer, model_patcher, tokenizer_name, trust_remote_code, revision, fast_inference, gpu_memory_utilization, float8_kv_cache, random_state, max_lora_rank, disable_log_stats, unsloth_vllm_standby, num_labels, qat_scheme, **kwargs)
   2202         model_patcher.pre_patch()
   2203         # For debugging - we use a download counter to see if environments are not breaking or if HF is down
-> 2204         get_statistics(kwargs.get("local_files_only", False))
   2205 
   2206         if dtype is None:

/usr/local/lib/python3.12/dist-packages/unsloth/models/_utils.py in get_statistics(local_files_only)
   1212         disable_progress_bars()
   1213         disabled = True
-> 1214     _get_statistics(None)
   1215     _get_statistics("repeat", force_download = False)
   1216     total_memory = (

/usr/local/lib/python3.12/dist-packages/unsloth/models/_utils.py in _get_statistics(statistics, force_download)
   1174                 time_limited_stats_check()
   1175             except TimeoutError:
-> 1176                 raise TimeoutError(
   1177                     "Unsloth: HuggingFace seems to be down after trying for 120 seconds :(\n"
   1178                     "Check https://status.huggingface.co/ for more details.\n"

TimeoutError: Unsloth: HuggingFace seems to be down after trying for 120 seconds :(
Check https://status.huggingface.co/ for more details.
As a temporary measure, use modelscope with the same model name ie:
```
pip install modelscope
import os; os.environ['UNSLOTH_USE_MODELSCOPE'] = '1'
from unsloth import FastLanguageModel
model = FastLanguageModel.from_pretrained('unsloth/gpt-oss-20b')
```

해결 방법이 있을까요? 강사님...