Add all missing Bedrock models#8
Open
adlio wants to merge 2 commits into
Open
Conversation
Add 19 new model definitions across 8 vendors: - Claude 3 (Haiku, Opus, Sonnet), Claude 3.5 (Haiku, Sonnet v1, Sonnet v2) - Cohere Command R, Command R+ v2 - Mistral Large 2, Mistral Small - Writer Palmyra X4, Palmyra X5 (new vendor) - Meta Llama 3 (70B, 8B) - Amazon Titan Text (Express, Lite, Premier) (new vendor) - AI21 Jamba (1.5 Large, 1.5 Mini, Instruct) (new vendor) Updated all model registries: vendor files, mod.rs tests, lib.rs re-exports, and model_verification.rs example. Co-authored-by: Aaron Longwell <27492+adlio@users.noreply.github.com>
Add 13 new models across 6 vendors: - Z.AI: GLM 5 - MiniMax: M2, M2.5 - NVIDIA: Nemotron Nano 2, Nemotron Nano 2 VL, Nemotron 3 Nano 30B A3B, Nemotron 3 Super 120B A12B - OpenAI: GPT OSS 20B, GPT OSS 120B, GPT OSS Safeguard 20B, GPT OSS Safeguard 120B - Mistral: Devstral 2 135B - Writer: Palmyra Vision 7B Create new vendor files nvidia.rs and openai.rs. Wire up all models in mod.rs, lib.rs, and model_verification.rs. Co-authored-by: Aaron Longwell <27492+adlio@users.noreply.github.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #8 +/- ##
==========================================
+ Coverage 88.45% 88.48% +0.02%
==========================================
Files 111 111
Lines 24212 24266 +54
==========================================
+ Hits 21417 21471 +54
Misses 2795 2795 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request was generated by @kiro-agent 👻
Comment with /kiro fix to address specific feedback or /kiro all to address everything.
Learn about Kiro autonomous agent
Adds 32 missing Bedrock text generation models across 14 vendors, sourced from the AWS Bedrock pricing page.
New vendor files:
nvidia.rs— Nemotron Nano 2, Nano 2 VL, 3 Nano 30B A3B, 3 Super 120B A12Bopenai.rs— GPT OSS 20B, 120B, Safeguard 20B, Safeguard 120Bai21.rs— Jamba 1.5 Large, 1.5 Mini, Instructtitan.rs— Titan Text Express, Lite, Premierwriter.rs— Palmyra X4, X5, Vision 7BUpdated vendor files:
claude.rs— Claude 3 Haiku/Opus/Sonnet, 3.5 Haiku/Sonnet v1/v2cohere.rs— Command R, Command R+ v2glm.rs— GLM 5llama.rs— Llama 3 70B, 8Bminimax.rs— MiniMax M2, M2.5mistral.rs— Mistral Large 2, Small, Devstral 2 135BAll models are wired up in
mod.rs,lib.rs, andmodel_verification.rs. Workspace compiles clean and all unit tests pass.Note on GLM 5.1: Not found on the Bedrock pricing page or AWS documentation as of this PR. The Z.AI section lists GLM 5, GLM 4.7, and GLM 4.7 Flash only.