Rewrite old function from modeling_opt.py

llava/model/language_model/mpt/hf_prefixlm_converter.py

@@ -18,8 +18,6 @@ from transformers.models.gpt_neo.modeling_gpt_neo import GPTNeoForCausalLM
 from transformers.models.gpt_neox.modeling_gpt_neox import GPTNeoXForCausalLM
 from transformers.models.gptj.modeling_gptj import GPTJForCausalLM
 from transformers.models.opt.modeling_opt import OPTForCausalLM
-from transformers.models.opt.modeling_opt import _expand_mask as _expand_mask_opt
-from transformers.models.opt.modeling_opt import _make_causal_mask as _make_causal_mask_opt
 logger = logging.get_logger(__name__)
 _SUPPORTED_GPT_MODELS = (GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM)
 CAUSAL_GPT_TYPES = Union[GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM]
@@ -52,6 +50,36 @@ def _expand_mask_bloom(mask: torch.Tensor, tgt_length: int) -> torch.BoolTensor:
     expanded_mask = ~(mask[:, None, None, :].to(torch.bool))
     return expanded_mask.expand(batch_size, 1, tgt_length, src_length)
 
+def _make_causal_mask_opt(
+    input_ids_shape: torch.Size, dtype: torch.dtype, device: torch.device, past_key_values_length: int = 0
+):
+    """
+    Make causal mask used for bi-directional self-attention.
+    """
+    bsz, tgt_len = input_ids_shape
+    mask = torch.full((tgt_len, tgt_len), torch.finfo(dtype).min, device=device)
+    mask_cond = torch.arange(mask.size(-1), device=device)
+    mask.masked_fill_(mask_cond < (mask_cond + 1).view(mask.size(-1), 1), 0)
+    mask = mask.to(dtype)
+
+    if past_key_values_length > 0:
+        mask = torch.cat([torch.zeros(tgt_len, past_key_values_length, dtype=dtype, device=device), mask], dim=-1)
+    return mask[None, None, :, :].expand(bsz, 1, tgt_len, tgt_len + past_key_values_length)
+
+
+def _expand_mask_opt(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
+    """
+    Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
+    """
+    bsz, src_len = mask.size()
+    tgt_len = tgt_len if tgt_len is not None else src_len
+
+    expanded_mask = mask[:, None, None, :].expand(bsz, 1, tgt_len, src_len).to(dtype)
+
+    inverted_mask = 1.0 - expanded_mask
+
+    return inverted_mask.masked_fill(inverted_mask.to(torch.bool), torch.finfo(dtype).min)
+
 def _convert_gpt_causal_lm_to_prefix_lm(model: CAUSAL_GPT_TYPES) -> CAUSAL_GPT_TYPES:
     """Converts a GPT-style Causal LM to a Prefix LM.