Skip to content

refactor: simplify Llama2Model constructor to take llm_config directly #11170

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

Closed
wants to merge 1 commit into from
Closed

refactor: simplify Llama2Model constructor to take llm_config directly #11170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion examples/models/llama/export_llama_lib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1226,7 +1226,7 @@ def _load_llama_model(
EagerModelFactory.create_model(
module_name,
model_class_name,
llm_config=llm_config,
model_args={"llm_config": llm_config},
)
)

Expand Down
13 changes: 6 additions & 7 deletions examples/models/llama/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,19 +36,18 @@ def convert_to_llama_checkpoint(**kwargs):


class Llama2Model(EagerModelBase):
def __init__(self, **kwargs):
def __init__(self, llm_config):
resource_dir = get_default_model_resource_dir(__file__)

self.llm_config = llm_config

# Use single checkpoint file.
checkpoint_path = kwargs.get("checkpoint", None)
checkpoint_path = self.llm_config.base.checkpoint
# Check if checkpoint_dir was provided for a sharded checkpoint.
checkpoint_dir = kwargs.get("checkpoint_dir", None)
checkpoint_dir = self.llm_config.base.checkpoint_dir

# Params file.
params_path = kwargs.get("params", None)

self.llm_config = kwargs.get("llm_config")
assert self.llm_config is not None, "llm_config must be provided"
params_path = self.llm_config.base.params

self.use_kv_cache = self.llm_config.model.use_kv_cache
self.use_sdpa_with_kv_cache_op = self.llm_config.model.use_sdpa_with_kv_cache
Expand Down
Loading