[BUG] ValueError: The following model_kwargs are not used by the model

[vyomakesh09]

Zephyr modal

################################

Traceback (most recent call last):
File "/home/v/inhouse/zephyr.py", line 5, in
output = model("Tell me a joke about programmers")
File "/home/v/.local/lib/python3.10/site-packages/swarms/models/zephyr.py", line 61, in call
outputs = self.pipe(prompt, max_new_token=self.max_new_tokens)
File "/home/v/.local/lib/python3.10/site-packages/transformers/pipelines/text_generation.py", line 208, in call
return super().call(text_inputs, **kwargs)
File "/home/v/.local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1140, in call
return self.run_single(inputs, preprocess_params, forward_params, postprocess_params)
File "/home/v/.local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1147, in run_single
model_outputs = self.forward(model_inputs, **forward_params)
File "/home/v/.local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1046, in forward
model_outputs = self._forward(model_inputs, **forward_params)
File "/home/v/.local/lib/python3.10/site-packages/transformers/pipelines/text_generation.py", line 271, in _forward
generated_sequence = self.model.generate(input_ids=input_ids, attention_mask=attention_mask, **generate_kwargs)
File "/home/v/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/v/.local/lib/python3.10/site-packages/transformers/generation/utils.py", line 1485, in generate
self._validate_model_kwargs(model_kwargs.copy())
File "/home/v/.local/lib/python3.10/site-packages/transformers/generation/utils.py", line 1262, in _validate_model_kwargs
raise ValueError(
ValueError: The following model_kwargs are not used by the model: ['max_new_token'] (note: typos in the generate arguments will also show up in this list)

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.