Last assistant response is not valid canvas: expected string or bytes-like object

Torcelllo commented 1 month ago

Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch(). You shouldn't move a model that is dispatched using accelerate hooks. Load to GPU: LlamaForCausalLM The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results. Setting pad_token_id to eos_token_id:128001 for open-end generation. Exception in thread Thread-11 (generate): Traceback (most recent call last): File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrapinner self.run() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run self._target(*self._args, self.kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 115, in decoratecontext return func(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\utils.py", line 1758, in generate result = self.sample( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\utils.py", line 2397, in sample outputs = self( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\hooks.py", line 166, in new_forward output = module._oldforward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modelingllama.py", line 1164, in forward outputs = self.model( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forwardcall(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\hooks.py", line 166, in new_forward output = module._oldforward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.py", line 940, in forward causal_mask = self._update_causalmask( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.py", line 1061, in _update_causal_mask causal_mask = torch.triu(causal_mask, diagonal=1) RuntimeError: "triu_tril_cudatemplate" not implemented for 'BFloat16' Traceback (most recent call last): File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 528, in process_events response = await route_utils.call_processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api output = await app.get_blocks().processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.callfunction( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.asynciteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper response = await iterator.anext() File "X:\Omost\chat_interface.py", line 554, in _stream_fn first_response, first_interrupter = await asynciteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 625, in anext return await anyio.to_thread.runsync( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_workerthread( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_workerthread return await future File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, args) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 608, in run_sync_iteratorasync return next(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) File "X:\Omost\gradio_app.py", line 164, in chatfn for text in streamer: File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\streamers.py", line 223, in next value = self.textqueue.get(timeout=self.timeout) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\queue.py", line 179, in get raise Empty queue.Empty Last assistant response is not valid canvas: expected string or bytes-like object Traceback (most recent call last): File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 528, in process_events response = await route_utils.call_processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api output = await app.get_blocks().processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.callfunction( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.asynciteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper response = await iterator.anext() File "X:\Omost\chat_interface.py", line 554, in _stream_fn first_response, first_interrupter = await asynciteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 625, in anext return await anyio.to_thread.runsync( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_workerthread( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_workerthread return await future File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, args) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 608, in run_sync_iteratorasync return next(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) File "X:\Omost\gradio_app.py", line 116, in chat_fn np.random.seed(int(seed)) File "numpy\random\mtrand.pyx", line 4806, in numpy.random.mtrand.seed File "numpy\random\mtrand.pyx", line 250, in numpy.random.mtrand.RandomState.seed File "_mt19937.pyx", line 168, in numpy.random._mt19937.MT19937._legacy_seeding File "_mt19937.pyx", line 182, in numpy.random._mt19937.MT19937._legacyseeding ValueError: Seed must be between 0 and 2**32 - 1 Last assistant response is not valid canvas: expected string or bytes-like object Traceback (most recent call last): File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 528, in process_events response = await route_utils.call_processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api output = await app.get_blocks().processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.callfunction( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.asynciteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper response = await iterator.anext() File "X:\Omost\chat_interface.py", line 554, in _stream_fn first_response, first_interrupter = await asynciteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 625, in anext return await anyio.to_thread.runsync( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_workerthread( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_workerthread return await future File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 608, in run_sync_iteratorasync return next(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) File "X:\Omost\gradio_app.py", line 116, in chat_fn np.random.seed(int(seed)) File "numpy\random\mtrand.pyx", line 4806, in numpy.random.mtrand.seed File "numpy\random\mtrand.pyx", line 250, in numpy.random.mtrand.RandomState.seed File "_mt19937.pyx", line 168, in numpy.random._mt19937.MT19937._legacy_seeding File "_mt19937.pyx", line 182, in numpy.random._mt19937.MT19937._legacy_seeding ValueError: Seed must be between 0 and 232 - 1 Last assistant response is not valid canvas: expected string or bytes-like object The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results. Setting pad_token_id to eos_token_id:128001 for open-end generation. Exception in thread Thread-12 (generate): Traceback (most recent call last): File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrapinner self.run() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run self._target(*self._args, *self.kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\utils.py", line 1758, in generate result = self.sample( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\utils.py", line 2397, in sample outputs = self( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forwardcall(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\hooks.py", line 166, in new_forward output = module._oldforward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modelingllama.py", line 1164, in forward outputs = self.model( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forwardcall(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\hooks.py", line 166, in new_forward output = module._oldforward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.py", line 940, in forward causal_mask = self._update_causalmask( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.py", line 1061, in _update_causal_mask causal_mask = torch.triu(causal_mask, diagonal=1) RuntimeError: "triu_tril_cudatemplate" not implemented for 'BFloat16' Traceback (most recent call last): File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 528, in process_events response = await route_utils.call_processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api output = await app.get_blocks().processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.callfunction( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.asynciteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper response = await iterator.anext() File "X:\Omost\chat_interface.py", line 554, in _stream_fn first_response, first_interrupter = await asynciteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 625, in anext return await anyio.to_thread.runsync( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_workerthread( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_workerthread return await future File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, args) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 608, in run_sync_iteratorasync return next(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) File "X:\Omost\gradio_app.py", line 164, in chatfn for text in streamer: File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\streamers.py", line 223, in next value = self.textqueue.get(timeout=self.timeout) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\queue.py", line 179, in get raise Empty _queue.Empty Last assistant response is not valid canvas: expected string or bytes-like object The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results. Setting pad_token_id to eos_token_id:128001 for open-end generation. Exception in thread Thread-13 (generate): Traceback (most recent call last): File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrapinner self.run() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run self._target(self._args, self.kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 115, in decoratecontext return func(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\utils.py", line 1758, in generate result = self.sample( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\utils.py", line 2397, in sample outputs = self( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\hooks.py", line 166, in new_forward output = module._oldforward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modelingllama.py", line 1164, in forward outputs = self.model( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forwardcall(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\hooks.py", line 166, in new_forward output = module._oldforward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.py", line 940, in forward causal_mask = self._update_causalmask( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.py", line 1061, in _update_causal_mask causal_mask = torch.triu(causal_mask, diagonal=1) RuntimeError: "triu_tril_cudatemplate" not implemented for 'BFloat16' Traceback (most recent call last): File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 528, in process_events response = await route_utils.call_processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api output = await app.get_blocks().processapi( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.callfunction( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.asynciteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper response = await iterator.anext() File "X:\Omost\chat_interface.py", line 554, in _stream_fn first_response, first_interrupter = await asynciteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 632, in asynciteration return await iterator.anext() File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 625, in anext return await anyio.to_thread.runsync( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_workerthread( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_workerthread return await future File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 608, in run_sync_iteratorasync return next(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) File "X:\Omost\gradio_app.py", line 164, in chatfn for text in streamer: File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\generation\streamers.py", line 223, in next value = self.textqueue.get(timeout=self.timeout) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\queue.py", line 179, in get raise Empty _queue.Empty Last assistant response is not valid canvas: expected string or bytes-like object

diodiogod commented 1 month ago

I have the same error

diodiogod commented 1 month ago

Well I don't know if you have the same problem as I did, but I have two GPUs. I barely know what I'm doing but after adding this line just below to the "import os" line on the "gradio_app.py" file it worked for me. os.environ['CUDA_VISIBLE_DEVICES'] = '0'

hutaiHang commented 4 weeks ago

RuntimeError: "triu_tril_cuda_template" not implemented for 'BFloat16'

This problem can be solved by https://huggingface.co/meta-llama/Meta-Llama-3-8B/discussions/34#:~:text=I%20solved%20my%20problem%20by%20replacing

supca commented 3 weeks ago

尝试使用以下方式进行修复，我已经修复了相同问题

第一步：编辑 pipeline.py 打开 pipeline.py 文件。找到以下代码行： alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32) 将其修改为： alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32).clone().detach() 第二步：编辑 modeling_llama.py 找到 modeling_llama.py 文件，通常它位于 E:\Omost\python\lib\site-packages\transformers\models\llama\ 目录中。找到以下代码行： causal_mask = torch.triu(causal_mask, diagonal=1) 将其修改为： causal_mask = torch.triu(causal_mask.to(torch.float32), diagonal=1)

aibymind commented 3 weeks ago

尝试使用以下方式进行修复，我已经修复了相同问题

Это сработало, спасибо! Только у меня не было папки python в каталоге C:\Omost\ Пришлось создать виртуальную среду venv, и уже в ней искать каталог lib\site-packages\transformers\models\llama\

MNeMoNiCuZ commented 2 weeks ago

Same error for me as well:

The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.
Traceback (most recent call last):
  File "C:\AI\Omost\venv\lib\site-packages\gradio\queueing.py", line 528, in process_events
    response = await route_utils.call_process_api(
  File "C:\AI\Omost\venv\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api
    output = await app.get_blocks().process_api(
  File "C:\AI\Omost\venv\lib\site-packages\gradio\blocks.py", line 1908, in process_api
    result = await self.call_function(
  File "C:\AI\Omost\venv\lib\site-packages\gradio\blocks.py", line 1497, in call_function
    prediction = await utils.async_iteration(iterator)
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 632, in async_iteration
    return await iterator.__anext__()
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper
    response = await iterator.__anext__()
  File "C:\AI\Omost\chat_interface.py", line 554, in _stream_fn
    first_response, first_interrupter = await async_iteration(generator)
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 632, in async_iteration
    return await iterator.__anext__()
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 625, in __anext__
    return await anyio.to_thread.run_sync(
  File "C:\AI\Omost\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "C:\AI\Omost\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2177, in run_sync_in_worker_thread
    return await future
  File "C:\AI\Omost\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run
    result = context.run(func, *args)
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 608, in run_sync_iterator_async
    return next(iterator)
  File "C:\AI\Omost\venv\lib\site-packages\torch\utils\_contextlib.py", line 35, in generator_context
    response = gen.send(None)
  File "C:\AI\Omost\gradio_app.py", line 164, in chat_fn
    for text in streamer:
  File "C:\AI\Omost\venv\lib\site-packages\transformers\generation\streamers.py", line 223, in __next__
    value = self.text_queue.get(timeout=self.timeout)
  File "C:\Python310\lib\queue.py", line 179, in get
    raise Empty
_queue.Empty
Last assistant response is not valid canvas: expected string or bytes-like object

runshengdu commented 1 week ago

Same error for me as well:

The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.
Traceback (most recent call last):
  File "C:\AI\Omost\venv\lib\site-packages\gradio\queueing.py", line 528, in process_events
    response = await route_utils.call_process_api(
  File "C:\AI\Omost\venv\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api
    output = await app.get_blocks().process_api(
  File "C:\AI\Omost\venv\lib\site-packages\gradio\blocks.py", line 1908, in process_api
    result = await self.call_function(
  File "C:\AI\Omost\venv\lib\site-packages\gradio\blocks.py", line 1497, in call_function
    prediction = await utils.async_iteration(iterator)
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 632, in async_iteration
    return await iterator.__anext__()
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 758, in asyncgen_wrapper
    response = await iterator.__anext__()
  File "C:\AI\Omost\chat_interface.py", line 554, in _stream_fn
    first_response, first_interrupter = await async_iteration(generator)
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 632, in async_iteration
    return await iterator.__anext__()
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 625, in __anext__
    return await anyio.to_thread.run_sync(
  File "C:\AI\Omost\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "C:\AI\Omost\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2177, in run_sync_in_worker_thread
    return await future
  File "C:\AI\Omost\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run
    result = context.run(func, *args)
  File "C:\AI\Omost\venv\lib\site-packages\gradio\utils.py", line 608, in run_sync_iterator_async
    return next(iterator)
  File "C:\AI\Omost\venv\lib\site-packages\torch\utils\_contextlib.py", line 35, in generator_context
    response = gen.send(None)
  File "C:\AI\Omost\gradio_app.py", line 164, in chat_fn
    for text in streamer:
  File "C:\AI\Omost\venv\lib\site-packages\transformers\generation\streamers.py", line 223, in __next__
    value = self.text_queue.get(timeout=self.timeout)
  File "C:\Python310\lib\queue.py", line 179, in get
    raise Empty
_queue.Empty
Last assistant response is not valid canvas: expected string or bytes-like object

did you fix it?

lllyasviel / Omost

Last assistant response is not valid canvas: expected string or bytes-like object #4