tao-finetune-cosmos-embed
暂无简介
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-13
- Stars
- ★ 2
- Forks
- 2
01 前言 Front Matter
- name
- tao-finetune-cosmos-embed
- tags
- [ "video", "vision-language", "vlm", "multimodal", "retrieval", "embedding", "cosmos", "fine-tuning" ]
- license
- Apache-2.0
- version
- 1.0.0 Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".
- category
- development-code
- metadata
- { "author": "NVIDIA Corporation", "version": "0.1.0" }
- description
- allowed-tools
- Read Bash
- compatibility
- Requires docker + nvidia-container-toolkit, the published Cosmos-Embed TAO container from versions.yaml, and a HuggingFace token when downloading pretrained `nvidia/Cosmos-Embed1-*` weights.
02 资源文件 10
- 参考文档BENCHMARK.md4.3 KB
- 参考文档evals/evals.json787 B
- 参考文档references/skill_info.yaml2.5 KB
- 参考文档references/spec_template_evaluate.yaml1.2 KB
- 参考文档references/spec_template_export_hf.yaml775 B
- 参考文档references/spec_template_export_onnx.yaml847 B
- 参考文档references/spec_template_inference.yaml1.1 KB
- 参考文档references/spec_template_train.yaml2.2 KB
- 参考文档skill-card.md4.0 KB
- 其他skill.oms.sig6.0 KB
03 SKILL.md 正文
Cosmos-Embed
Cosmos-Embed1 is a joint video-text embedder for text-to-video retrieval, video-to-video search, zero-shot/kNN classification, and semantic deduplication. The packaged CLI is cosmos-embed1 and supports train, evaluate, inference, and export.
Container image and per-action commands are in references/skill_info.yaml. Compact starting specs are in references/spec_template_*.yaml.
Train Action Policy
This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skill_info.yaml and resolve the run override from either an explicit automl_policy value or the user's workflow request. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as automl_policy: off for this run only; otherwise default to auto. When automl_policy: auto, automl_enabled: true, and both schemas/train.schema.json and references/spec_template_train.yaml are packaged, route the train action through tao-skill-bank:tao-run-automl by default with this model's skill_dir. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and automl_policy. Use direct model training only when automl_policy: off or the packaged train schema/template is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.
Non-train actions such as evaluate, inference, export, and deploy flows stay in this model skill. The per-run automl_policy override does not change model metadata.
Quick Start
Use the published Cosmos-Embed container declared by references/skill_info.yaml
and resolved through versions.yaml. Do not build from the private
Cosmos-Embed1 source tree for normal skill use; build from source only when
developing the container itself.
TAO_SKILL_BANK_PATH="${TAO_SKILL_BANK_PATH:-$PWD}"
COSMOS_EMBED_IMAGE="${COSMOS_EMBED_IMAGE:-$(
python "$TAO_SKILL_BANK_PATH/scripts/resolve_tao_image.py" \
--skill-bank "$TAO_SKILL_BANK_PATH" \
--model cosmos-embed \
--action train \
--format json |
python -c 'import json,sys; print(json.load(sys.stdin)["image"])'
)}"
docker pull "$COSMOS_EMBED_IMAGE"
Expected local workspace layout:
workspace/
├── data/
│ ├── msrvtt_test_1k.json
│ └── video/
│ ├── video7020.mp4
│ └── ...
├── model/
│ └── Cosmos-Embed1-224p/ # optional if using HF repo id
├── specs/
│ ├── train.yaml
│ ├── evaluate.yaml
│ ├── inference.yaml
│ ├── export_onnx.yaml
│ └── export_hf.yaml
└── results/
Use these Docker options for all actions unless the local Docker/platform skill gives a stricter environment-specific command:
TAO_SKILL_BANK_PATH="${TAO_SKILL_BANK_PATH:-$PWD}"
COSMOS_EMBED_IMAGE="${COSMOS_EMBED_IMAGE:-$(
python "$TAO_SKILL_BANK_PATH/scripts/resolve_tao_image.py" \
--skill-bank "$TAO_SKILL_BANK_PATH" \
--model cosmos-embed \
--action train \
--format json |
python -c 'import json,sys; print(json.load(sys.stdin)["image"])'
)}"
RUN_ROOT="${RUN_ROOT:-$PWD}"
DOCKER_COMMON=(
--rm --gpus all --ipc=host --network=host
--shm-size=64g
--ulimit memlock=-1
--ulimit stack=67108864
-e HF_TOKEN
-v "$RUN_ROOT/data:/data:ro"
-v "$RUN_ROOT/model:/model"
-v "$RUN_ROOT/specs:/specs:ro"
-v "$RUN_ROOT/results:/results"
)
Train:
docker run "${DOCKER_COMMON[@]}" "$COSMOS_EMBED_IMAGE" \
cosmos-embed1 train -e /specs/train.yaml results_dir=/results
Evaluate:
docker run "${DOCKER_COMMON[@]}" "$COSMOS_EMBED_IMAGE" \
cosmos-embed1 evaluate -e /specs/evaluate.yaml results_dir=/results
Inference:
docker run "${DOCKER_COMMON[@]}" "$COSMOS_EMBED_IMAGE" \
cosmos-embed1 inference -e /specs/inference.yaml \
'inference.query.input_texts=["a man is singing on stage"]' \
inference.k=5 \
results_dir=/results
Export ONNX:
docker run "${DOCKER_COMMON[@]}" "$COSMOS_EMBED_IMAGE" \
cosmos-embed1 export -e /specs/export_onnx.yaml \
export.checkpoint=/results/train/cosmos_embed1_model_latest.pth \
export.onnx_file=/results/export/cosmos_embed1_combined.onnx \
results_dir=/results
Export HuggingFace format:
docker run "${DOCKER_COMMON[@]}" "$COSMOS_EMBED_IMAGE" \
cosmos-embed1 export -e /specs/export_hf.yaml \
export.checkpoint=/results/train/cosmos_embed1_model_latest.pth \
export.hf_output_dir=/results/export_hf/cosmos_embed1_hf \
results_dir=/results
Smoke Overrides
For a small functional check, keep the same specs and override the expensive knobs:
train.max_iter=1
train.validation_iter=2
train.checkpoint_iter=1
train.optim.optim=adamw
dataset.train_dataset.batch_size=1
dataset.val_dataset.batch_size=1
dataset.train_dataset.workers=0
dataset.val_dataset.workers=0
If no local Cosmos-Embed1 pretrained checkpoint or HuggingFace token is available, set model.pretrained_model_path=null for a plumbing-only smoke train. The model quality is meaningless in that mode, but the train/evaluate/inference/export action paths can still be exercised.
For evaluation and inference smoke tests on a tiny subset:
evaluate.callbacks.embedding_visualization=false
evaluate.callbacks.max_eval_samples=8
dataset.test_dataset.batch_size=1
dataset.test_dataset.workers=0
inference.k=2
dataset.inference_dataset.batch_size=1
dataset.inference_dataset.workers=0
Data Format
The MSR-VTT path expects a local video glob and a JSON metadata file:
dataset:
train_dataset:
dataset_type: msrvtt
mp4_urls: /data/video/*.mp4
metadata: /data/msrvtt_test_1k.json
List-format metadata rows must include at least video and caption:
{"video_id": "video7020", "video": "video7020.mp4", "caption": "a woman creating a fondant baby and flower"}
The dataset loader derives the video id from the local .mp4 filename and filters to videos present in the metadata. If a run finds zero videos, check that mp4_urls points to a container-local glob and that metadata video names match the filenames.
Model Weights
- Local HF directory: mount it under
/modeland setmodel.pretrained_model_path=/model/Cosmos-Embed1-224p. - HuggingFace repo: set
model.pretrained_model_path=nvidia/Cosmos-Embed1-224pand passHF_TOKENif access is gated. - Fine-tuned checkpoint: downstream actions default to
/results/train/cosmos_embed1_model_latest.pth.
Variants:
| Variant | Resolution | Frames | Embedding dim |
|---|---|---|---|
Cosmos-Embed1-224p |
224 x 224 | 8 | 256 |
Cosmos-Embed1-336p |
336 x 336 | 8 | 768 |
Cosmos-Embed1-448p |
448 x 448 | 8 | 768 |
Keep model.network.embed_dim, model.input_hw, and model.network.spatial_resolution aligned with the selected variant.
Important Parameters
| Parameter | Notes |
|---|---|
train.num_gpus |
1 for single GPU, >1 auto-launches torchrun, -1 auto-detects visible GPUs. |
train.max_iter |
Main training length. Use 1 only for smoke testing. |
train.optim.optim |
fused_adamw is faster when available; adamw is safer for smoke and portability. |
model.lora.enabled |
Enables LoRA. Set model.network.visual_encoder.transformer_engine=false when LoRA is on. |
model.lora.lora_rank |
LoRA rank. Start with 8; try 4, 8, or 16 for manual or AutoML-style sweeps. |
model.lora.lora_alpha |
LoRA scaling factor. Start with 16; keep near 2 * lora_rank unless experiments show otherwise. |
model.lora.lora_dropout |
LoRA dropout. Start with 0.1; sweep 0.0, 0.05, and 0.1 for small datasets. |
model.lora.bias |
Bias policy: none, all, or lora_only. Keep none unless intentionally training biases. |
model.lora.use_rslora / use_dora |
Optional LoRA variants. Enable one at a time and record the setting with the checkpoint. |
model.lora.target_modules |
Optional module-name patterns for LoRA injection. Leave empty for the default ViT + Q-Former attention/MLP targets. |
model.lora.modules_to_save |
Optional modules to keep fully trainable alongside LoRA. Leave empty unless preserving a task-specific head. |
evaluate.load_dataset_pkl / save_dataset_pkl |
Cache evaluation embeddings. |
inference.load_dataset_pkl / save_dataset_pkl |
Cache the search database for repeated retrieval. |
export.mode |
video, text, combined, or huggingface. |
export.on_cpu |
Recommended for export to avoid device mismatch issues. |
LoRA and AutoML Notes
For parameter-efficient fine-tuning, set model.lora.enabled=true and keep
model.network.visual_encoder.transformer_engine=false; TAO Core's
Cosmos-Embed1 config notes that PEFT cannot inject adapters into Transformer
Engine layers. Treat the LoRA fields above as the first candidate parameters
for manual tuning or AutoML-style search before unfreezing larger model blocks.
Avoid changing target_modules or modules_to_save unless the user explicitly
needs custom adapter placement.
S3 Staging
The Cosmos-Embed1 CLI consumes local paths and Python globs, not raw s3://.../*.mp4 URIs. For S3-backed runs, first stage a subset or full dataset to the execution host/container filesystem, then use local paths such as /data/video/*.mp4 in the spec.
Recommended S3 layout for staged MSR-VTT data:
s3://bucket/path/cosmos-embed/msrvtt-subset/
├── msrvtt_test_1k.json
└── video/
├── video7020.mp4
└── ...
After downloading/syncing that prefix into the mounted data/ directory, use the same Docker commands above.
Outputs
results/
├── train/
│ ├── cosmos_embed1_model_latest.pth
│ ├── cosmos_embed1_model_<iter>.pth
│ └── experiment.yaml
├── evaluate/
│ ├── metrics.json
│ └── experiment.yaml
├── inference/
│ ├── results.json
│ └── experiment.yaml
├── export/
│ ├── cosmos_embed1_combined.onnx
│ └── export_config.yaml
└── export_hf/
└── cosmos_embed1_hf/
Known Pitfalls
| Symptom | Cause | Fix |
|---|---|---|
MSRVTTDataset: 0 videos found |
mp4_urls is not a local glob or metadata filenames do not match videos. |
Mount data into the container and set mp4_urls=/data/video/*.mp4. |
| HF download/auth failure | Missing or invalid HF_TOKEN, or model agreement not accepted. |
Accept the model terms and pass -e HF_TOKEN. |
| LoRA injection failure | Transformer Engine visual encoder is enabled. | Set model.network.visual_encoder.transformer_engine=false. |
| ONNX/HF export complains about missing components | Export checkpoint is partial or adapter-only. | Use a full checkpoint or configure pretrained visual/text sources before export. |
| CUDA OOM | Batch/resolution too high for the GPU. | Reduce batch size, use 224p, enable LoRA, or use more GPUs. |
04 同仓库更多 Skills
yingmi-skill
当用户需要查询基金、策略、公告、财经资讯,做资产配置、组合诊断、风险回测、现金流分析,或生成图表、PDF 时,优先使用本 Skill 获取真实数据与可执行能力。
web-access
所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、网络交互等。
tencentmap-map-assistant
腾讯位置服务·地图助手 Skill,一句自然语言调用腾讯地图全套能力,无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索(含评分/人均/营业时间)、关键词提示、路线规划(驾车/步行/公交/骑行)、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询,并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。
skill-scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.
shader-dev
Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.