Can't load tokenizer for 'elinas/llama-7b-hf-transformers-4.29' #94
Description
total vram = 96869.25
required vram(full=13858, 8bit=8254, 4bit=5140)
determined model type: alpaca
Traceback (most recent call last):
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/gradio/routes.py", line 437, in run_predict
output = await app.get_blocks().process_api(
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/gradio/blocks.py", line 1352, in process_api
result = await self.call_function(
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/gradio/blocks.py", line 1077, in call_function
prediction = await anyio.to_thread.run_sync(
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
File "/home/16tb_hdd/xxc/LLM-As-Chatbot/app.py", line 291, in download_completed
global_vars.initialize_globals(tmp_args)
File "/home/16tb_hdd/xxc/LLM-As-Chatbot/global_vars.py", line 176, in initialize_globals
model, tokenizer = load_model(
File "/home/16tb_hdd/xxc/LLM-As-Chatbot/models/alpaca.py", line 17, in load_model
tokenizer = LlamaTokenizer.from_pretrained(
File "/home/xiaoxingchen/.conda/envs/llm-serve/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 1830, in from_pretrained
raise EnvironmentError(
OSError: Can't load tokenizer for 'elinas/llama-7b-hf-transformers-4.29'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'elinas/llama-7b-hf-transformers-4.29' is the correct path to a directory containing all relevant files for a LlamaTokenizer tokenizer.
Hi, I'm having this issue right now.
Can anyone tell me how to fix it?