google

/

recurrentgemma-9b-it

like 49

Follow

Google 4,123

Hi!

I tried to run example from readme:

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/recurrentgemma-9b-it")
model = AutoModelForCausalLM.from_pretrained("google/recurrentgemma-9b-it", device_map="auto")

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

but got error RecurrentGemmaForCausalLM.forward() got an unexpected keyword argument 'position_ids'

Can you help to resolve the issue?

I am using transformers==4.44.0, accelerate==0.33.0, torch==2.3.1+cu118, python==3.11.9.

full traceback

TypeError                                 Traceback (most recent call last)
Cell In[1], line 9
      6 input_text = "Write me a poem about Machine Learning."
      7 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
----> 9 outputs = model.generate(**input_ids)
     10 print(tokenizer.decode(outputs[0]))

File ~/envs/py3.11_pt2_cu11.8/lib/python3.11/site-packages/torch/utils/_contextlib.py:115, in context_decorator.<locals>.decorate_context(*args, **kwargs)
    112 @functools.wraps(func)
    113 def decorate_context(*args, **kwargs):
    114     with ctx_factory():
--> 115         return func(*args, **kwargs)

File ~/envs/py3.11_pt2_cu11.8/lib/python3.11/site-packages/transformers/generation/utils.py:2024, in GenerationMixin.generate(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)
   2016     input_ids, model_kwargs = self._expand_inputs_for_generation(
   2017         input_ids=input_ids,
   2018         expand_size=generation_config.num_return_sequences,
   2019         is_encoder_decoder=self.config.is_encoder_decoder,
   2020         **model_kwargs,
   2021     )
   2023     # 13. run sample (it degenerates to greedy search when `generation_config.do_sample=False`)
-> 2024     result = self._sample(
   2025         input_ids,
   2026         logits_processor=prepared_logits_processor,
   2027         logits_warper=prepared_logits_warper,
   2028         stopping_criteria=prepared_stopping_criteria,
   2029         generation_config=generation_config,
   2030         synced_gpus=synced_gpus,
   2031         streamer=streamer,
   2032         **model_kwargs,
   2033     )
   2035 elif generation_mode in (GenerationMode.BEAM_SAMPLE, GenerationMode.BEAM_SEARCH):
   2036     # 11. prepare logits warper
   2037     prepared_logits_warper = (
   2038         self._get_logits_warper(generation_config, device=input_ids.device)
   2039         if generation_config.do_sample
   2040         else None
   2041     )

File ~/envs/py3.11_pt2_cu11.8/lib/python3.11/site-packages/transformers/generation/utils.py:2982, in GenerationMixin._sample(self, input_ids, logits_processor, stopping_criteria, generation_config, synced_gpus, streamer, logits_warper, **model_kwargs)
   2979 model_inputs.update({"output_hidden_states": output_hidden_states} if output_hidden_states else {})
   2981 # forward pass to get next token
-> 2982 outputs = self(**model_inputs, return_dict=True)
   2984 if synced_gpus and this_peer_finished:
   2985     continue  # don't waste resources running the code we don't need

File ~/envs/py3.11_pt2_cu11.8/lib/python3.11/site-packages/torch/nn/modules/module.py:1532, in Module._wrapped_call_impl(self, *args, **kwargs)
   1530     return self._compiled_call_impl(*args, **kwargs)  # type: ignore[misc]
   1531 else:
-> 1532     return self._call_impl(*args, **kwargs)

File ~/envs/py3.11_pt2_cu11.8/lib/python3.11/site-packages/torch/nn/modules/module.py:1541, in Module._call_impl(self, *args, **kwargs)
   1536 # If we don't have any hooks, we want to skip the rest of the logic in
   1537 # this function, and just call forward.
   1538 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
   1539         or _global_backward_pre_hooks or _global_backward_hooks
   1540         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1541     return forward_call(*args, **kwargs)
   1543 try:
   1544     result = None

File ~/envs/py3.11_pt2_cu11.8/lib/python3.11/site-packages/accelerate/hooks.py:169, in add_hook_to_module.<locals>.new_forward(module, *args, **kwargs)
    167         output = module._old_forward(*args, **kwargs)
    168 else:
--> 169     output = module._old_forward(*args, **kwargs)
    170 return module._hf_hook.post_forward(module, output)

TypeError: RecurrentGemmaForCausalLM.forward() got an unexpected keyword argument 'position_ids'