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

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 bootstrap_inner 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 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.old_forward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.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 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.old_forward(*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_causal_mask( 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_cuda_template" 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_process_api( 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().process_api( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.call_function( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.async_iteration(iterator) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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 async_iteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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.run_sync( 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_worker_thread( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread 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_iterator_async 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 chat_fn 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.text_queue.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_process_api( 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().process_api( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.call_function( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.async_iteration(iterator) File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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 async_iteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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.run_sync( 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_worker_thread( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread 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_iterator_async 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 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_process_api( 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().process_api( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.call_function( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.async_iteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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 async_iteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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.run_sync( 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_worker_thread( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread 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_iterator_async 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 2**32 - 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 bootstrap_inner 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 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.old_forward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.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 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.old_forward(*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_causal_mask( 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_cuda_template" 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_process_api( 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().process_api( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1908, in process_api result = await self.call_function( File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1497, in call_function prediction = await utils.async_iteration(iterator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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 async_iteration(generator) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\\utils.py", line 632, in async_iteration 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.run_sync( 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_worker_thread( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread 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_iterator_async 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 chat_fn 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.text_queue.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 bootstrap_inner 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 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.old_forward(*args, **kwargs) File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\llama\modeling_llama.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 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.old_forward(*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_causal_mask( 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_cuda_template" 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_process_api( 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().process_api( File "C:\Users\john_\AppData\Local\Programs\Python\Python310\lib\site-p