tiiuae

/

falcon-7b-instruct

like 876

Hi All.

I am getting the following Could not locate the configuration_RW.py inside tiiuae/falcon-7b-instruct. error since this morning. From my understanding it is related to the following change to the Falcon model.

Usecase
I have fine tuned the falcon-7b-instruct model using SFT and use the following snippet to load the model:

sft_model_16 = AutoModelForCausalLM.from_pretrained(
    model_dir,
    device_map="auto",
    trust_remote_code=True,
    torch_dtype=torch.float16,
)

The model_dir includes the base model along with the adaptor.

I am using 4.27.4 of the transformers library. Prior to the latest commit, the instantiated model was of the RWForCausalLM type.

RWForCausalLM(
  (transformer): RWModel(
    (word_embeddings): Embedding(65024, 4544)
    (h): ModuleList(
      (0-31): 32 x DecoderLayer(
        (input_layernorm): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
        (self_attention): Attention(
          (maybe_rotary): RotaryEmbedding()
          (query_key_value): Linear(in_features=4544, out_features=4672, bias=False)
          (dense): Linear(in_features=4544, out_features=4544, bias=False)
          (attention_dropout): Dropout(p=0.0, inplace=False)
        )
        (mlp): MLP(
          (dense_h_to_4h): Linear(in_features=4544, out_features=18176, bias=False)
          (act): GELU(approximate='none')
          (dense_4h_to_h): Linear(in_features=18176, out_features=4544, bias=False)
        )
      )
    )
    (ln_f): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
  )
  (lm_head): Linear(in_features=4544, out_features=65024, bias=False)
)

After the latest commit, the instantiated model was of the FalconForCausalLM type.

FalconForCausalLM(
  (transformer): FalconModel(
    (word_embeddings): Embedding(65024, 4544)
    (h): ModuleList(
      (0-31): 32 x FalconDecoderLayer(
        (self_attention): FalconAttention(
          (maybe_rotary): FalconRotaryEmbedding()
          (query_key_value): FalconLinear(in_features=4544, out_features=4672, bias=False)
          (dense): FalconLinear(in_features=4544, out_features=4544, bias=False)
          (attention_dropout): Dropout(p=0.0, inplace=False)
        )
        (mlp): FalconMLP(
          (dense_h_to_4h): FalconLinear(in_features=4544, out_features=18176, bias=False)
          (act): GELU(approximate='none')
          (dense_4h_to_h): FalconLinear(in_features=18176, out_features=4544, bias=False)
        )
        (input_layernorm): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
      )
    )
    (ln_f): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
  )
  (lm_head): Linear(in_features=4544, out_features=65024, bias=False)
)

What is the recommended way to resolve this error and safe guarding against this scenario in the future?

Thanks in advance.