riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Jamba - Skip 4d custom attention mask test (#30826)

Browse Source 
* Jamba - Skip 4d custom attention mask test

* Skip assistant greedy test
This commit is contained in:
amyeroberts 2024-05-15 13:57:28 +01:00 committed by GitHub
parent a42844955f
commit 64c06df325
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/transformers/models/jamba/modeling_jamba.py
View File

@ -1261,7 +1261,6 @@ class JambaPreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True
_supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module):
std = self.config.initializer_range

4
tests/models/jamba/test_modeling_jamba.py
View File

@ -502,6 +502,10 @@ class JambaModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi
# They should result in very similar logits
self.assertTrue(torch.allclose(next_logits_wo_padding, next_logits_with_padding, atol=3e-3))
@unittest.skip("Jamba has its own special cache type") # FIXME: @gante
def test_assisted_decoding_matches_greedy_search_0_random(self):
pass
@require_flash_attn
@require_torch_gpu
@require_bitsandbytes