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

Jump to bottom

Add Phi 3 128k model #1800

Merged
merged 3 commits into from
Oct 23, 2024
Merged

Add Phi 3 128k model #1800

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a49e648
Update config.py
deveworld Oct 23, 2024
4d7fd41
Update test_model.py
deveworld Oct 23, 2024
f4ddfac
Update download_model_weights.md
deveworld Oct 23, 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
18 changes: 18 additions & 0 deletions litgpt/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1660,6 +1660,24 @@ def norm_class(self) -> Type:
sliding_window_size=2048,
sliding_window_layer_placing="all",
),
# https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/blob/main/config.json
dict(
name="Phi-3-mini-128k-instruct",
hf_config=dict(org="microsoft", name="Phi-3-mini-128k-instruct"),
vocab_size=32000,
padded_vocab_size=32064,
block_size=131072,
n_embd=3072,
n_layer=32,
rotary_percentage=1.0,
bias=False,
norm_class_name="RMSNorm",
intermediate_size=8192,
mlp_class_name="LLaMAMLP",
parallel_residual=False,
sliding_window_size=262145,
sliding_window_layer_placing="all",
),
# https://huggingface.co/microsoft/Phi-3.5-mini-instruct/blob/main/config.json
dict(
name="Phi-3.5-mini-instruct",
Expand Down
2 changes: 1 addition & 1 deletion tests/test_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -324,7 +324,7 @@ def test_against_hf_phi(model_name, device, dtype):


@torch.inference_mode()
@pytest.mark.parametrize("model_name", ("Phi-3-mini-4k-instruct", "Phi-3.5-mini-instruct"))
@pytest.mark.parametrize("model_name", ("Phi-3-mini-4k-instruct", "Phi-3-mini-128k-instruct", "Phi-3.5-mini-instruct"))
@pytest.mark.parametrize(
("device", "dtype"),
[
Expand Down
1 change: 1 addition & 0 deletions tutorials/download_model_weights.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,6 +137,7 @@ meta-llama/Meta-Llama-3.1-8B
meta-llama/Meta-Llama-3.1-8B-Instruct
microsoft/phi-1_5
microsoft/phi-2
microsoft/Phi-3-mini-128k-instruct
microsoft/Phi-3-mini-4k-instruct
microsoft/Phi-3.5-mini-instruct
mistralai/mathstral-7B-v0.1
Expand Down
Loading