Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add StableLM #28810

Merged
merged 11 commits into from
Feb 14, 2024
Merged

Add StableLM #28810

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
81bebe9
Add `StableLM`
jon-tow Feb 1, 2024
6a6a0ca
fix(model): re-create from `huggingface-cli add-new-model-like persim…
jon-tow Feb 6, 2024
d1b843b
Merge branch 'main' of https://github.com/huggingface/transformers in…
jon-tow Feb 13, 2024
59559f7
fix: re-add changes to address comments
jon-tow Feb 13, 2024
50c14dd
fix(readme): add links to paper
jon-tow Feb 13, 2024
6f1a2c5
fix(tokenization_auto): remove `GPTNeoXTokenizerFastFast` ref
jon-tow Feb 13, 2024
fe0a498
fix(tests): re-add `@slow` decorator to integration tests
jon-tow Feb 13, 2024
717e129
fix(tests): import slow...
jon-tow Feb 13, 2024
f46f869
fix(readme_hd): remove whitespace edit
jon-tow Feb 13, 2024
5930bf6
fix(tokenizer): auto tokenizer tuple
jon-tow Feb 13, 2024
ae0df72
skip doctests for `modeling_stablelm`
jon-tow Feb 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix(tests): re-add @slow decorator to integration tests
  • Loading branch information
@jon-tow
jon-tow committed Feb 13, 2024
commit fe0a498be2260dc00d113861301b49144dee3d97
6 changes: 3 additions & 3 deletions tests/models/stablelm/test_modeling_stablelm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -382,7 +382,7 @@ def test_model_rope_scaling(self, scaling_type):

@require_torch
class StableLmModelIntegrationTest(unittest.TestCase):
# @slow
@slow
def test_model_stablelm_3b_4e1t_logits(self):
input_ids = {"input_ids": torch.tensor([[510, 8588, 310, 1900, 9386]], dtype=torch.long, device=torch_device)}

Expand All @@ -399,7 +399,7 @@ def test_model_stablelm_3b_4e1t_logits(self):
EXPECTED_SLICE = torch.tensor([7.1030, -1.4195, 9.9206, 7.7008, 4.9891, 4.2169, 5.5426, 3.7878, 6.7593, 5.7360, 8.4691, 5.5448, 5.0544, 10.4129, 8.5573, 13.0405, 7.3265, 3.5868, 6.1106, 5.9406, 5.6376, 5.7490, 5.4850, 4.8124, 5.1991, 4.6419, 4.5719, 9.9588, 6.7222, 4.5070]).to(torch_device) # fmt: skip
self.assertTrue(torch.allclose(output[0, 0, :30], EXPECTED_SLICE, atol=1e-4, rtol=1e-4))

# @slow
@slow
def test_model_stablelm_3b_4e1t_generation(self):
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t")
model = StableLmForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t")
Expand All @@ -415,7 +415,7 @@ def test_model_stablelm_3b_4e1t_generation(self):
self.assertEqual(text, EXPECTED_TEXT_COMPLETION)

@require_bitsandbytes
# @slow
@slow
@require_flash_attn
def test_model_3b_long_prompt(self):
EXPECTED_OUTPUT_TOKEN_IDS = [3, 3, 3]
Expand Down