ByteDance

/

Sa2VA-4B

like 69

Follow

ByteDance 1.47k

Hi,
Thanks a lot for sharing the model,
I'm trying to make it work from the Quick start code shared on the HF page, but I'm facing an issue. Here is the error I get:

/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py in _sample(self, input_ids, logits_processor, stopping_criteria, generation_config, synced_gpus, streamer, **model_kwargs)
   3249 
   3250             if is_prefill:
-> 3251                 outputs = self(**model_inputs, return_dict=True)
   3252                 is_prefill = False
   3253             else:

TypeError: Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(151679, 2048)
    (layers): ModuleList(
      (0-35): 36 x Qwen2DecoderLayer(
        (self_attn): Qwen2FlashAttention2(
          (q_proj): Linear(in_features=2048, out_features=2048, bias=True)
          (k_proj): Linear(in_features=2048, out_features=256, bias=True)
          (v_proj): Linear(in_features=2048, out_features=256, bias=True)
          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
          (rotary_emb): Qwen2RotaryEmbedding()
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=2048, out_features=11008, bias=False)
          (up_proj): Linear(in_features=2048, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=2048, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((2048,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=2048, out_features=151679, bias=False)
) got multiple values for keyword argument 'return_dict'

It seems there is a problem with Qwen.

I work on colab enterprise with 2 A100 GPUs.

Any idea that could help to solve the problem ?

Thanks in advance