blog
blog copied to clipboard
Falcon-40B thread problem.
history: [['You are World renown expert on quantum mechanics and the Bell inequality. Do you understand? ', '']]
Exception in thread Thread-10 (generate_and_signal_complete):
Traceback (most recent call last):
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/threading.py", line 1009, in _bootstrap_inner
self.run()
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/threading.py", line 946, in run
self._target(*self._args, **self._kwargs)
File "/tmp/ipykernel_6551/331460570.py", line 122, in generate_and_signal_complete
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/transformers/generation/utils.py", line 1568, in generate
return self.sample(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/transformers/generation/utils.py", line 2615, in sample
outputs = self(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/developer/.cache/huggingface/modules/transformers_modules/falcon-40b-instruct/modelling_RW.py", line 759, in forward
transformer_outputs = self.transformer(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/developer/.cache/huggingface/modules/transformers_modules/falcon-40b-instruct/modelling_RW.py", line 654, in forward
outputs = block(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/developer/.cache/huggingface/modules/transformers_modules/falcon-40b-instruct/modelling_RW.py", line 396, in forward
attn_outputs = self.self_attention(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/developer/.cache/huggingface/modules/transformers_modules/falcon-40b-instruct/modelling_RW.py", line 252, in forward
fused_qkv = self.query_key_value(hidden_states) # [batch_size, seq_length, 3 x hidden_size]
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/developer/.cache/huggingface/modules/transformers_modules/falcon-40b-instruct/modelling_RW.py", line 32, in forward
ret = input @ self.weight.T
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling cublasCreate(handle)
Traceback (most recent call last):
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/gradio/routes.py", line 422, in run_predict
output = await app.get_blocks().process_api(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/gradio/blocks.py", line 1323, in process_api
result = await self.call_function(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/gradio/blocks.py", line 1067, in call_function
prediction = await utils.async_iteration(iterator)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/gradio/utils.py", line 336, in async_iteration
return await iterator.anext()
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/gradio/utils.py", line 329, in anext
return await anyio.to_thread.run_sync(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/gradio/utils.py", line 312, in run_sync_iterator_async
return next(iterator)
File "/tmp/ipykernel_6551/331460570.py", line 147, in bot
for new_text in streamer:
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/site-packages/transformers/generation/streamers.py", line 223, in next
value = self.text_queue.get(timeout=self.timeout)
File "/home/developer/mambaforge/envs/Guanaco/lib/python3.10/queue.py", line 179, in get
raise Empty
_queue.Empty