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.

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 GPT-4o model #2649

Merged
merged 2 commits into from
May 15, 2024
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
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 setup.cfg
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ mistral =

openai =
openai~=1.0
tiktoken~=0.3.3
tiktoken~=0.7
pydantic~=2.0 # For model_dump(mode="json") - openai only requires pydantic>=1.9.0

google =
Expand Down
7 changes: 7 additions & 0 deletions src/helm/config/model_deployments.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -1348,6 +1348,13 @@ model_deployments:
client_spec:
class_name: "helm.clients.openai_client.OpenAIClient"

- name: openai/gpt-4o-2024-05-13
model_name: openai/gpt-4o-2024-05-13
tokenizer_name: openai/o200k_base
max_sequence_length: 128000
client_spec:
class_name: "helm.clients.openai_client.OpenAIClient"

- name: openai/gpt-4-vision-preview
model_name: openai/gpt-4-vision-preview
tokenizer_name: openai/cl100k_base
Expand Down
8 changes: 8 additions & 0 deletions src/helm/config/model_metadata.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -1806,6 +1806,14 @@ models:
release_date: 2024-04-09
tags: [TEXT_MODEL_TAG, OPENAI_CHATGPT_MODEL_TAG, LIMITED_FUNCTIONALITY_TEXT_MODEL_TAG, INSTRUCTION_FOLLOWING_MODEL_TAG]

- name: openai/gpt-4o-2024-05-13
display_name: GPT-4o (2024-05-13)
description: GPT-4o (2024-05-13) is a large multimodal model that accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs.
creator_organization_name: OpenAI
access: limited
release_date: 2024-04-09
tags: [TEXT_MODEL_TAG, OPENAI_CHATGPT_MODEL_TAG, LIMITED_FUNCTIONALITY_TEXT_MODEL_TAG, INSTRUCTION_FOLLOWING_MODEL_TAG]

- name: openai/gpt-4-vision-preview
# According to https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4, this model has pointed gpt-4-1106-vision-preview.
display_name: GPT-4V (1106 preview)
Expand Down
6 changes: 6 additions & 0 deletions src/helm/config/tokenizer_configs.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -288,6 +288,12 @@ tokenizer_configs:
end_of_text_token: "<|endoftext|>"
prefix_token: "<|endoftext|>"

- name: openai/o200k_base
tokenizer_spec:
class_name: "helm.tokenizers.tiktoken_tokenizer.TiktokenTokenizer"
end_of_text_token: "<|endoftext|>"
prefix_token: "<|endoftext|>"

- name: openai/clip-vit-large-patch14
tokenizer_spec:
class_name: "helm.tokenizers.huggingface_tokenizer.HuggingFaceTokenizer"
Expand Down