tiiuae/falcon-7b-instruct : ValueError: The following `model_kwargs` are not used by the model: ['token_type_ids']

[vsraptor]

In [7]: x=LLM()
tiiuae/falcon-7b-instruct

Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:06<00:00,  3.31s/it]
Model processing is set on CPU. 


In [8]: x.lm.predict('hi')


/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py:1201: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation)
  warnings.warn(
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-8-421d79812622> in <module>
----> 1 x.lm.predict('hi')

/usr/local/lib/python3.10/dist-packages/panml/llm/huggingface.py in predict(self, text, max_length, skip_special_tokens, display_probability, num_return_sequences, temperature, top_p, top_k, no_repeat_ngram_size, prompt_modifier, keep_history)
    285 
    286                 # Call model for text generation
--> 287                 output_context = self._predict(context, max_length=max_length, skip_special_tokens=skip_special_tokens,
    288                                                display_probability=display_probability, num_return_sequences=num_return_sequences,
    289                                                temperature=temperature, top_p=top_p, top_k=top_k, no_repeat_ngram_size=no_repeat_ngram_size)

/usr/local/lib/python3.10/dist-packages/panml/llm/huggingface.py in _predict(self, text, max_length, skip_special_tokens, display_probability, num_return_sequences, temperature, top_p, top_k, no_repeat_ngram_size)
    190 
    191         input_batch = self.tokenizer(text, return_tensors='pt').to(torch.device(self.device))
--> 192         output = self.model_hf.generate(**input_batch, 
    193                                         max_length=max_length,
    194                                         pad_token_id=self.model_hf.config.eos_token_id,

/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py in decorate_context(*args, **kwargs)
    113     def decorate_context(*args, **kwargs):
    114         with ctx_factory():
--> 115             return func(*args, **kwargs)
    116 
    117     return decorate_context

/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py in generate(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, **kwargs)
   1211         model_kwargs = generation_config.update(**kwargs)  # All unused kwargs must be model kwargs
   1212         generation_config.validate()
-> 1213         self._validate_model_kwargs(model_kwargs.copy())
   1214 
   1215         # 2. Set generation parameters if not already defined

/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py in _validate_model_kwargs(self, model_kwargs)
   1103 
   1104         if unused_model_args:
-> 1105             raise ValueError(
   1106                 f"The following `model_kwargs` are not used by the model: {unused_model_args} (note: typos in the"
   1107                 " generate arguments will also show up in this list)"

ValueError: The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)

In [9]: