Skip to content

Adds new metrics calculated #64

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Adds new metrics calculated #64

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
19 changes: 15 additions & 4 deletions tests/models/test_decoders.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@
GRANITE_3p3_8B_INSTRUCT = "ibm-granite/granite-3.3-8b-instruct"
GRANITE_20B_CODE_INSTRUCT_8K = "ibm-granite/granite-20b-code-instruct-8k"
LLAMA_3p1_70B_INSTRUCT = "meta-llama/Llama-3.1-70B-Instruct"
MISTRAL_0p3_7B_INSTRUCT = "mistralai/Mistral-7B-Instruct-v0.3"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same comment as above, this should be added as part of the config here: #60


micro_model_mapping = {
LLAMA_3p1_8B_INSTRUCT: os.path.join(MICRO_MODELS_HOME, "llama-3.1-8b-layers-3-step-24000"),
Expand Down Expand Up @@ -72,6 +73,7 @@
GRANITE_3p3_8B_INSTRUCT,
GRANITE_20B_CODE_INSTRUCT_8K,
LLAMA_3p1_70B_INSTRUCT,
MISTRAL_0p3_7B_INSTRUCT
],
)
# for validation level 1, the default is a failure rate of 1%
Expand Down Expand Up @@ -145,25 +147,34 @@
# threshold key is (model_id, is_tiny_model)
fail_thresholds = {
(LLAMA_3p1_8B_INSTRUCT, False): (
2.6994638133048965,
0.00047589250549208347,
2.7080255031585696,
0.0004068055667448795,
),
(GRANITE_3p2_8B_INSTRUCT, False): (
2.3919514417648315,
0.0005767398688476533,
),
(GRANITE_3p2_8B_INSTRUCT, True): (
2.7449850964546205,
0.00018840670207282534,
),
(GRANITE_3p3_8B_INSTRUCT, False): (
2.4444521379470827,
0.0004970188625156878,
),
(GRANITE_20B_CODE_INSTRUCT_8K, False): (
2.640706129074097,
0.00034344267623964697,
2.646075320243838,
0.0003458251833217223,
),
# TODO: run llama 70B with 1,2,4,8 batches
(LLAMA_3p1_70B_INSTRUCT, False): (
2.841279556751251,
0.0044301633024588115,
),
(MISTRAL_0p3_7B_INSTRUCT, False): (
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can this be added to #60 (rather than directly in this file)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi! Ok, so do I create a new file like the one in the PR #60 or the idea is to append all models to that same file?

2.846206340789795,
0.0008768103783950205,
),
}
# custom weight adaptation to be used in future. For instance if we would like to add some other adaptation, we can register it with this custom adapter
# and provide it when converting from an aiu fms model's weights to a cpu fms model's weights. Currently this is only done for gptq, but may be done for other
Expand Down