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 Mistral Small and Mistral Large #2399

Merged
merged 3 commits into from
Feb 26, 2024
Merged

Add Mistral Small and Mistral Large #2399

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
3287248
Add Mistral Small and Mistral Large
yifanmai Feb 26, 2024
e72976d
Fix tags
yifanmai Feb 26, 2024
c5c7768
Fix dates
yifanmai Feb 26, 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: 16 additions & 2 deletions src/helm/config/model_deployments.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -909,8 +909,22 @@ model_deployments:
args:
mistral_model: "mistral-tiny"

- name: mistralai/mistral-medium
model_name: mistralai/mistral-medium
- name: mistralai/mistral-small-2402
model_name: mistralai/mistral-small-2402
tokenizer_name: mistralai/Mistral-7B-v0.1
max_sequence_length: 32000
client_spec:
class_name: "helm.proxy.clients.mistral_client.MistralAIClient"

- name: mistralai/mistral-medium-2312
model_name: mistralai/mistral-medium-2312
tokenizer_name: mistralai/Mistral-7B-v0.1
max_sequence_length: 32000
client_spec:
class_name: "helm.proxy.clients.mistral_client.MistralAIClient"

- name: mistralai/mistral-large-2402
model_name: mistralai/mistral-large-2402
tokenizer_name: mistralai/Mistral-7B-v0.1
max_sequence_length: 32000
client_spec:
Expand Down
25 changes: 22 additions & 3 deletions src/helm/config/model_metadata.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1168,14 +1168,33 @@ models:
release_date: 2023-10-16
tags: [VISION_LANGUAGE_MODEL_TAG, LLAVA_MODEL_TAG, LIMITED_FUNCTIONALITY_VLM_TAG]

- name: mistralai/mistral-medium
display_name: Mistral medium
- name: mistralai/mistral-small-2402
display_name: Mistral Small (2402)
# TODO: Fill in description
description: TBD
creator_organization_name: Mistral AI
access: closed
# Blog post: https://mistral.ai/news/mistral-large/
release_date: 2023-02-26
tags: [TEXT_MODEL_TAG, LIMITED_FUNCTIONALITY_TEXT_MODEL_TAG, INSTRUCTION_FOLLOWING_MODEL_TAG]

- name: mistralai/mistral-medium-2312
display_name: Mistral Medium (2312)
description: Mistral is a transformer model that uses Grouped-Query Attention (GQA) and Sliding-Window Attention (SWA).
creator_organization_name: Mistral AI
access: closed
release_date: 2023-12-11
tags: [TEXT_MODEL_TAG, FULL_FUNCTIONALITY_TEXT_MODEL_TAG, INSTRUCTION_FOLLOWING_MODEL_TAG]
tags: [TEXT_MODEL_TAG, LIMITED_FUNCTIONALITY_TEXT_MODEL_TAG, INSTRUCTION_FOLLOWING_MODEL_TAG]

- name: mistralai/mistral-large-2402
display_name: Mistral Large
# TODO: Fill in description
description: TBD
creator_organization_name: Mistral AI
access: closed
# Blog post: https://mistral.ai/news/mistral-large/
release_date: 2023-02-26
tags: [TEXT_MODEL_TAG, LIMITED_FUNCTIONALITY_TEXT_MODEL_TAG, INSTRUCTION_FOLLOWING_MODEL_TAG]


# MosaicML
Expand Down
Loading