How do I install the Litert Model Equivalence Test skill?

Run npx skillmds@latest add google-ai-edge/litert-model-equivalence-test in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Litert Model Equivalence Test safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Litert Model Equivalence Test?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Litert Model Equivalence Test free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Litert Model Equivalence Test?

google-ai-edge (@google-ai-edge) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Litert Model Equivalence Test by google-ai-edge

Name: Litert Model Equivalence Test
Author: google-ai-edge

Litert Model Equivalence Test

Validates equivalence between LiteRT models (litert_lm) and PyTorch models (transformers). Use when you need to verify that an exported LiteRT model produces the same outputs as the original Hugging Face model. Supports multi-turn conversations and custom prompts.

google-ai-edge 1a57e1e 3 files · 15.6 KB Updated Sep 17, 2026

File contents

LiteRT Model Equivalence Test

This skill provides instructions for running equivalence tests between LiteRT models and their PyTorch source models.

Usage

Use the equivalence_test script to compare the outputs of a Hugging Face model and its exported LiteRT version.

Running the Test

Run the test using bazel run from your workspace:

bazel run \
  //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \
  -- \
  --model_id={model_id} \
  [--prompt={prompt}] \
  [--prompt_file={prompt_file}] \
  [--max_new_tokens={max_new_tokens}] \
  [--max_num_tokens={max_num_tokens}] \
  [--work_dir={work_dir}] \
  [--externalize_embedder] \
  [--single_token_embedder] \
  [--split_cache] \
  [--backend={backend}]

Flags

--model_id: The Hugging Face model ID to validate (e.g., google/gemma-3-270m-it).
--prompt: Prompt to test. Specify multiple times for multi-turn conversations.
--prompt_file: Path to a file containing one (complex) prompt. Overrides --prompt.
--max_new_tokens: Maximum new tokens to generate per turn (default: 20).
--max_num_tokens: KV cache length for the model (default: 2048).
--work_dir: Base directory for model export. If not specified, a temporary directory under HOME is used.
--externalize_embedder: Externalize the embedder during export (default: False).
--single_token_embedder: Use single token embedder during export (default: False).
--split_cache: Split KV cache during export (default: False).
--backend: Hardware backend to use for LiteRT LM (cpu | npu, default: cpu).

Examples

Single-turn test with custom prompt:

bazel run \
  //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \
  -- \
  --model_id=google/gemma-3-270m-it \
  --prompt="What is the capital of France?"

Multi-turn test:

bazel run \
  //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \
  -- \
  --model_id=google/gemma-3-270m-it \
  --prompt="What's the capital of France?" \
  --prompt="How about Germany?"

Testing with a prompt file:

bazel run \
  //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \
  -- \
  --model_id=google/gemma-3-270m-it \
  --prompt_file=/path/to/prompts.txt

Testing with externalized embedder:

bazel run \
  //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \
  -- \
  --model_id=google/gemma-3-270m-it \
  --externalize_embedder \
  --single_token_embedder

Testing NPU export variant:

bazel run \
  //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \
  -- \
  --model_id=google/gemma-3-270m-it \
  --externalize_embedder \
  --split_cache \
  --backend=npu

---name: litert-model-equivalence-testdescription: Validates equivalence between LiteRT models (litert_lm) and PyTorch models (transformers). Use when you need to verify that an exported LiteRT model produces the same outputs as the original Hugging Face model. Supports multi-turn conversations and custom prompts.---# LiteRT Model Equivalence TestThis skill provides instructions for running equivalence tests between LiteRTmodels and their PyTorch source models.## UsageUse the `equivalence_test` script to compare the outputs of a Hugging Face modeland its exported LiteRT version.### Running the TestRun the test using `bazel run` from your workspace:```bashbazel run \ //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \ -- \ --model_id={model_id} \ [--prompt={prompt}] \ [--prompt_file={prompt_file}] \ [--max_new_tokens={max_new_tokens}] \ [--max_num_tokens={max_num_tokens}] \ [--work_dir={work_dir}] \ [--externalize_embedder] \ [--single_token_embedder] \ [--split_cache] \ [--backend={backend}]```### Flags* `--model_id`: The Hugging Face model ID to validate (e.g., `google/gemma-3-270m-it`).* `--prompt`: Prompt to test. Specify multiple times for multi-turn conversations.* `--prompt_file`: Path to a file containing one (complex) prompt. Overrides `--prompt`.* `--max_new_tokens`: Maximum new tokens to generate per turn (default: 20).* `--max_num_tokens`: KV cache length for the model (default: 2048).* `--work_dir`: Base directory for model export. If not specified, a temporary directory under `HOME` is used.* `--externalize_embedder`: Externalize the embedder during export (default: False).* `--single_token_embedder`: Use single token embedder during export (default: False).* `--split_cache`: Split KV cache during export (default: False).* `--backend`: Hardware backend to use for LiteRT LM (cpu | npu, default: cpu).### Examples#### Single-turn test with custom prompt:```bashbazel run \ //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \ -- \ --model_id=google/gemma-3-270m-it \ --prompt="What is the capital of France?"```#### Multi-turn test:```bashbazel run \ //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \ -- \ --model_id=google/gemma-3-270m-it \ --prompt="What's the capital of France?" \ --prompt="How about Germany?"```#### Testing with a prompt file:```bashbazel run \ //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \ -- \ --model_id=google/gemma-3-270m-it \ --prompt_file=/path/to/prompts.txt```#### Testing with externalized embedder:```bashbazel run \ //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \ -- \ --model_id=google/gemma-3-270m-it \ --externalize_embedder \ --single_token_embedder```#### Testing NPU export variant:```bashbazel run \ //third_party/py/litert_torch/generative/export_hf/experimental/validation:equivalence_test \ -- \ --model_id=google/gemma-3-270m-it \ --externalize_embedder \ --split_cache \ --backend=npu```

Frequently asked questions