Update index.md
7eff1ccd
Rebase
14961a27
Rebase
b67ff241
Updates from make fixup
0aa10032
Update zamba.md
5e886530
Batched inference
123d9597
Update
f35bdf93
Fix tests
4d3f8c07
Fix tests
e51113da
Fix tests
cf6ee16c
pglorio
force pushed
to
cf6ee16c
1 year ago
Update docs/source/en/model_doc/zamba.md
f80b813a
Update docs/source/en/model_doc/zamba.md
c010a68f
Update configuration_zamba.py
9c3abc87
Update src/transformers/models/zamba/modeling_zamba.py
5d3d6154
Update src/transformers/models/zamba/modeling_zamba.py
d245749b
Update src/transformers/models/zamba/modeling_zamba.py
663343de
Update src/transformers/models/zamba/modeling_zamba.py
b3540eaa
Update modeling_zamba.py
554c14c2
Update modeling_zamba.py
c9c97fd6
Update modeling_zamba.py
ec9edd7c
Update configuration_zamba.py
939d6a91
Update modeling_zamba.py
c26addd3
Update modeling_zamba.py
e3c93f02
Merge branch 'main' of https://github.com/Zyphra/transformers_zamba
58d8c2dd
Update ZambaForCausalLM
396ebff5
Update ZambaForCausalLM
df8dfd30
Describe diffs with original mamba layer
4ab88a29
Moved mamba init into `_init_weights`
1a521de3
Moved mamba weight init into _init_weights
767a5911
Update index.md
d5b2beb2
Rebase
029813b9
Rebase
bec7dce7
Updates from make fixup
db153483
Update zamba.md
6c7f812e
Batched inference
c3766ba7
Update
dff24b86
Fix tests
245d9d9c
Fix tests
8aedd305
Fix tests
f8ed17a1
Update docs/source/en/model_doc/zamba.md
a5d5873c
Update docs/source/en/model_doc/zamba.md
17cef258
Update configuration_zamba.py
f773f120
Update src/transformers/models/zamba/modeling_zamba.py
c5852aa0
Update src/transformers/models/zamba/modeling_zamba.py
da64b363
Update src/transformers/models/zamba/modeling_zamba.py
7679578d
Update src/transformers/models/zamba/modeling_zamba.py
85fe7cb1
Update modeling_zamba.py
6c949c6e
Update modeling_zamba.py
f78b627a
Update modeling_zamba.py
3b3605a9
Update configuration_zamba.py
f6fc1e8f
Update modeling_zamba.py
d5b8d6e5
Update modeling_zamba.py
c2428a47
Merge branch 'main' of https://github.com/Zyphra/transformers_zamba
bbc9a8e3
Update ZambaForCausalLM
b13fdde1
Moved mamba init into `_init_weights`
037b9380
Update ZambaForCausalLM
9a1ef16a
Describe diffs with original mamba layer
d9d436c4
Merge branch 'main' of https://github.com/Zyphra/transformers_zamba
0bbb6c9a
make fixup fixes
91bc0767
quality test fixes
8f0100ff
Fix Zamba model path
7478e251
circleci fixes
a7c9d17a
circleci fixes
c2d097f6
circleci fixes
37881969
circleci fixes
1c6cca86
circleci fixes
911a78a2
circleci fixes
c6f2b3f9
circleci fixes
df931325
circleci fixes
211a5b50
circleci fixes
e0cb9fe3
Update
1df30bbd
circleci fixes
3d2800b8
Merge branch 'huggingface:main' into main
1e6f38be
fix zamba test from merge
d93377d0
fix ValueError for disabling mamba kernels
d01d80d9
add HF copyright
b9e86b05
shared_transf --> shared_transformer
4b0fb525
Update src/transformers/models/zamba/modeling_zamba.py
66b72c8e
Update src/transformers/models/zamba/modeling_zamba.py
d527a144
Fixes
97c646c2
Move attention head dim to config
1e4ffe6d
Fix circle/ci tests
2c53db25
Merge branch 'huggingface:main' into main
9a1ad324
Update modeling_zamba.py
a7717f28
apply GenerationMixin inheritance change from upstream
0fae3983
apply import ordering
0304440f
Merge branch 'huggingface:main' into main
3d9ec8e1
Merge branch 'main' into main
cb1d1d9a
Merge branch 'huggingface:main' into main
efcf16a0
update needed transformers version for zamba
339d4ccc
add contribution author
a46a26ba
add @slow to avoid CI
d0c1bc10
Merge branch 'huggingface:main' into main
4fcd130e
Update src/transformers/models/zamba/modeling_zamba.py
8d299644
Define attention_hidden_size
0381c337
Merge branch 'huggingface:main' into main
75554d8b
Added doc for attention_head_size
a109b3fc
trigger CI
9c10afe0
Fix doc of attention_hidden_size
18804555
Merge branch 'huggingface:main' into main
daef5b0b
[run-slow] zamba
347f7614
Merge branch 'huggingface:main' into main
634837f3
Merge branch 'huggingface:main' into main
4e8db07e
Fixed shared layer logic, swapped up<->gate in mlp
15047741
fix shared layer logic, swap up<->gate in mlp
06e3a7a5
shared_transformer -> shared_transf
267530d9
reformat HybridLayer __init__
0a90fc70
Merge branch 'huggingface:main' into main
fabaaecb
fix docstrings in zamba config
75f0d893
added definition of _get_input_ids_and_config
b9545eb4
fixed formatting of _get_input_ids_and_config
cdbd6906
Merge branch 'huggingface:main' into main
6fabb6a7
Merge branch 'huggingface:main' into main
b9f6cce8
Assignees
No one assigned
Labels
New model
run-slow
Login to write a write a comment.
Login via GitHub