ValueError: 0 unrecognized or not available.

[firmai]

Great project btw, really love the idea, have you been working on similar projects in the meantime?

---

ValueError Traceback (most recent call last)

in <cell line: 1>()
----> 1 cc = CausalChain(chunks)
2 cc.create_connections()
3 biggest_chain = cc.biggest_chain
4 cc.visualize(biggest_chain)

3 frames

/usr/local/lib/python3.10/dist-packages/causal_chains/CausalChain.py in init(self, chunks, device)
29 class CausalChain:
30 def init(self,chunks=[], device="cpu"):
---> 31 self.summarizer = pipeline("summarization", model="taskload/bart-cause-effect", device=0)
32 self.embmodel = SentenceTransformer('sentence-transformers/all-mpnet-base-v1').to(device)
33 self.chunks = chunks

/usr/local/lib/python3.10/dist-packages/transformers/pipelines/init.py in pipeline(task, model, config, tokenizer, feature_extractor, image_processor, framework, revision, use_fast, token, device, device_map, torch_dtype, trust_remote_code, model_kwargs, pipeline_class, **kwargs)
1095 kwargs["device"] = device
1096
-> 1097 return pipeline_class(model=model, framework=framework, task=task, **kwargs)

/usr/local/lib/python3.10/dist-packages/transformers/pipelines/text2text_generation.py in init(self, *args, **kwargs)
65
66 def init(self, *args, **kwargs):
---> 67 super().init(*args, **kwargs)
68
69 self.check_model_type(

/usr/local/lib/python3.10/dist-packages/transformers/pipelines/base.py in init(self, model, tokenizer, feature_extractor, image_processor, modelcard, framework, task, args_parser, device, torch_dtype, binary_output, **kwargs)
880 self.device = torch.device(f"mps:{device}")
881 else:
--> 882 raise ValueError(f"{device} unrecognized or not available.")
883 else:
884 self.device = device if device is not None else -1

ValueError: 0 unrecognized or not available.