wehub-resource-sync
e06fe8e8c6
Secret Leaks / trufflehog (push) Failing after 1s
Build documentation / build (push) Failing after 1s
Build documentation / build_other_lang (push) Failing after 0s
CodeQL Security Analysis / CodeQL Analysis (push) Failing after 0s
PR CI / pr-ci (push) Failing after 1s
Slow tests on important models (on Push - A10) / Get all modified files (push) Failing after 1s
Slow tests on important models (on Push - A10) / Model CI (push) Has been skipped
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
import torch
|
|
|
|
from transformers.modeling_outputs import CausalLMOutputWithPast
|
|
from transformers.models.llama.modeling_llama import LlamaModel
|
|
|
|
from ...cache_utils import Cache
|
|
|
|
|
|
# example where we need some deps and some functions
|
|
class SuperModel(LlamaModel):
|
|
def forward(
|
|
self,
|
|
input_ids: torch.LongTensor = None,
|
|
attention_mask: torch.Tensor | None = None,
|
|
position_ids: torch.LongTensor | None = None,
|
|
past_key_values: Cache | None = None,
|
|
inputs_embeds: torch.FloatTensor | None = None,
|
|
use_cache: bool | None = None,
|
|
output_attentions: bool | None = None,
|
|
output_hidden_states: bool | None = None,
|
|
return_dict: bool | None = None,
|
|
) -> tuple | CausalLMOutputWithPast:
|
|
out = super().forward(
|
|
input_ids,
|
|
attention_mask,
|
|
position_ids,
|
|
past_key_values,
|
|
inputs_embeds,
|
|
use_cache,
|
|
output_attentions,
|
|
output_hidden_states,
|
|
return_dict,
|
|
)
|
|
out.logits *= 2**4
|
|
return out
|