Add nvidia provider with 15 models#48
Open
TF0rd wants to merge 1 commit into
Open
Conversation
Add model parameter catalog entries for all NVIDIA NIM API models (provider: nvidia, authType: api_key) with parameters sourced from the official NVIDIA API reference at docs.api.nvidia.com. Models added: - nemotron-3-ultra-550b-a55b (reasoning_effort, reasoning_budget) - nemotron-3-super-120b-a12b (reasoning_effort, reasoning_budget) - nemotron-3-nano-30b-a3b - nemotron-mini-4b-instruct (tools support) - nemotron-content-safety-reasoning-4b - llama-3.1-nemotron-nano-8b-v1 - llama-3.1-nemotron-ultra-253b-v1 - llama-3.3-nemotron-super-49b-v1 - llama-3.3-nemotron-super-49b-v1.5 (65536 max_tokens) - llama-3.1-nemotron-safety-guard-8b-v3 - llama-3.1-nemoguard-8b-topic-control - riva-translate-4b-instruct-v1.1 - usdcode-llama-3.1-70b-instruct (expert_type enum) - gliner-pii (entity extraction: labels, threshold, chunk_length, overlap, flat_ner) - nemoguard-jailbreak-detect Two models omitted — their infer pages document only stream (a reserved MPS path not eligible as a parameter): - llama-3.1-nemoguard-8b-content-safety - nvidia-nemotron-nano-9b-v2 (infer page appears buggy; serves content-safety model data)
|
@TF0rd is attempting to deploy a commit to the Manifest Team on Vercel. A member of the Team first needs to authorize it. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Type of change
Summary
Adds the
nvidiaprovider with 15 model entries sourced from the official NVIDIA NIM API reference at docs.api.nvidia.com/nim/reference/llm-apis#nvidia.Each model's parameters were scraped from its
-inferendpoint documentation (e.g. nemotron-3-ultra-550b-a55b-infer).Models added
nemotron-3-ultra-550b-a55bnemotron-3-super-120b-a12bnemotron-3-nano-30b-a3bnemotron-mini-4b-instructnemotron-content-safety-reasoning-4bllama-3.1-nemotron-nano-8b-v1llama-3.1-nemotron-ultra-253b-v1llama-3.3-nemotron-super-49b-v1llama-3.3-nemotron-super-49b-v1.5llama-3.1-nemotron-safety-guard-8b-v3llama-3.1-nemoguard-8b-topic-controlriva-translate-4b-instruct-v1.1usdcode-llama-3.1-70b-instructgliner-piinemoguard-jailbreak-detectModels omitted
Two
nvidia/models were not added because their infer pages document onlystream(a reserved MPS path that cannot be a parameter):llama-3.1-nemoguard-8b-content-safety— only stream, accept, model, messagesnvidia-nemotron-nano-9b-v2— infer page appears buggy (serves content-safety model data)Checks
npm run validate— OK (189 models)npm test— 101/101 passednpm run guard:params— no removalsDocs