adding-model-support

A guide for adding support for a new language or vision-language model to Megatron-Bridge, a framework that connects model definitions to Megatron training. It covers examining the model configuration, creating the bridge and provider, adding recipes, tests, documentation, and examples.

In plain words
What is it for?
Inspecting a model configuration, registering a new architecture, implementing its provider and training recipe, and adding tests and documentation.
Why use it?
It provides a defined path for supporting a model instead of relying on guesswork. It highlights configuration details that affect registration, architecture handling, and weight conversion.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nvidia-nemo/megatron-bridge/adding-model-support
Any agent
npx skills add NVIDIA-NeMo/Megatron-Bridge --skill adding-model-support
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Megatron-Bridge

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,973 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.04973
Opus 5 $0.00018 $0.02486
Sonnet 5 $0.00007 $0.00995
Haiku 4.5 $0.00004 $0.00497

Measured 3d ago against content hash ad38996e271d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adding-model-support scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/adding-model-support/SKILL.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding New Model Support in Megatron-Bridge

Phase 1: Discovery

Step 1 — Get the HF model link

Ask the user for the HuggingFace model link (e.g. https://huggingface.co/Qwen/Qwen3.5-VL-27B).

If the model is not public, ask the user to provide the config.json file directly.

Step 2 — Fetch and analyze config.json

Read the model's config.json from HuggingFace (or from the user-provided file). Key fields to extract:

  • model_type — used for @register_bridge(model_type=...)
  • architectures — the HF model class name (used for source=... in registration)
  • tie_word_embeddings — critical for weight tying
  • Architecture fields: num_hidden_layers, hidden_size, intermediate_size, num_attention_heads, num_key_value_heads, vocab_size, max_position_embeddings, rope_theta, etc.
  • MoE fields (if present): num_local_experts, num_experts_per_tok, moe_intermediate_size
  • MLA fields (if present): q_lora_rank, kv_lora_rank, qk_nope_head_dim, qk_rope_head_dim

If there are config fields you don't recognize from previously supported models (check CONFIG_MAPPING in model_bridge.py and existing bridges), this likely indicates a new architectural block (e.g., a novel attention variant, custom normalization, or a new layer type). Ask the user to provide the HuggingFace modeling_*.py implementation of that block so you can understand the computation and create the correct Megatron-side mapping or custom module.

Step 3 — Determine VLM vs LLM

VLM (Vision-Language Model) if config.json contains:

  • text_config AND vision_config sub-configs
  • Note: VLMs may or may not have "VL" in the name

LLM (Text-only) if:

  • No text_config / vision_config
  • Single flat config for the language model

This distinction affects:

  • Which files to create (VLMs need a model.py combining vision + language)
  • Where to read config fields from (text_config vs top-level for VLMs)
  • Test patterns (VLMs need vision inputs in functional tests)

Read the full file on GitHub · 463 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 463 lines · 36 tokens per session scan A ad38996e271d

Subscribe to this mod's changes

adding-model-support is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (893 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 4,973 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…

google/skills · 104 tokens

ondb

A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…

x-cmd/x-cmd · 71 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Orchestra-Research/AI-Research-SKILLs · 58 tokens