huggingface/skills

"name": "Hugging Face"   },   "homepage": "https://github.com/huggingface/skills",

},   "homepage": "https://github.com/huggingface/skills",   "repository": "https://github.com/huggingface/skills",

"homepage": "https://github.com/huggingface/skills",

"repository": "https://github.com/huggingface/skills",

Connect AI assistants to the Hugging Face Hub. Setup: https://huggingface.co/settings/mcp

1. hf_doc_search(query="LoRA fine-tuning", product="peft") 2. hf_doc_fetch(doc_url="https://huggingface.co/docs/peft/...")

2. hf_doc_fetch(doc_url="https://huggingface.co/docs/peft/...")

[Credential-related source omitted]

[Credential-related source omitted]

Install: `curl -LsSf https://hf.co/cli/install.sh | bash -s`.

Install: `curl -LsSf https://hf.co/cli/install.sh | bash -s`.

- `hf cache rm TARGETS` — Remove cached repositories, revisions or files. `[--cache-dir TEXT --yes --dry-run --format [auto|human|agent|json|quiet]]`

To mount Hub repositories or buckets as local filesystems — no download, no copy, no waiting — use `hf-mount`. Files are fetched on demand. GitHub: https://github.com/huggingface/hf-mount

Install: `brew install hf-mount`, or download a binary from https://github.com/huggingface/hf-mount/releases

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

The bundled deploy scripts (`deploy.py`, `deploy_async.py`, `teardown.py`) use `boto3` directly and read image URIs from [AWS's published Deep Learning Containers catalog](https://aws.github.io/deep-learning-containers/reference/available_i

The SageMaker Python SDK (v3) is fine to use when the user prefers it or their project already does. Since [PR #5960](https://github.com/aws/sagemaker-python-sdk/pull/5960) (June 2026), `ModelBuilder` auto-routes HuggingFace models to the c

#!/usr/bin/env python

#!/usr/bin/env python3

installer = "uv" if shutil.which("uv") else "venv"     if installer == "venv":         log("uv not found — falling back to python + venv. Consider: https://docs.astral.sh/uv/")

log("uv not found — falling back to python + venv. Consider: https://docs.astral.sh/uv/")

#!/usr/bin/env python3

#!/usr/bin/env python3

The agent reads the image URI from AWS's [Deep Learning Containers catalog](https://aws.github.io/deep-learning-containers/reference/available_images/) — pick the row that matches the model family (HuggingFace vLLM for LLMs, TEI for embeddi

Executable file

#!/usr/bin/env python

#!/usr/bin/env python

#!/usr/bin/env python

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

URL: https://aws.github.io/deep-learning-containers/reference/available_images/

The example URLs use `763104351884` as the account ID for most regions. A few regions use different accounts (e.g. `eu-south-1` uses `692866216735`). Check the [Region Availability page](https://aws.github.io/deep-learning-containers/refere

**Do not use TGI.** Text Generation Inference is archived. Models released after the archive (Qwen3 most famously) fail ping health checks on TGI. Use vLLM instead. (The SageMaker SDK v3 agrees: since [PR #5960](https://github.com/aws/sagem

curl -s https://huggingface.co/<model-id>/raw/main/config.json

1. Open https://aws.github.io/deep-learning-containers/reference/available_images/

**Note on the TEI account ID**: the catalog page shows `683313688378` as the example account, but TEI is published from a different account namespace than the main AWS DLCs and the per-region account IDs vary. If `683313688378.dkr.ecr.<regi

curl -s https://api.github.com/repos/aws/deep-learning-containers/contents/docs/src/data/huggingface-vllm

curl -s https://raw.githubusercontent.com/aws/deep-learning-containers/main/docs/src/data/huggingface-vllm/0.21.0-gpu-sagemaker.yml

3. [Release notes on the DLC GitHub repo](https://github.com/aws/deep-learning-containers/releases).

The canonical source for AWS Deep Learning Container image URIs is: **https://aws.github.io/deep-learning-containers/reference/available_images/**

**https://aws.github.io/deep-learning-containers/reference/available_images/**

The SageMaker SDK v2 helper `get_huggingface_llm_image_uri` returned TGI URIs; the v3 SDK removed it entirely. Since [sagemaker-python-sdk PR #5960](https://github.com/aws/sagemaker-python-sdk/pull/5960) (merged June 2026), v3's `ModelBuild

- **Encoder cross-encoders** (BAAI/bge-reranker-*, mixedbread rerankers): BERT-family + classification head, `config.json` `architectures` ends in `ForSequenceClassification`. TEI serves these natively via its `/rerank` route. - **Generativ

- **Generative rerankers** (Qwen/Qwen3-Reranker-0.6B/4B/8B and similar): decoder-only causal LMs that emit a yes/no judgment token; relevance = P(yes)/(P(yes)+P(no)) from the logprobs. `config.json` `architectures` ends in `ForCausalLM`. Th

Listed on the AWS catalog under "HuggingFace Text Embeddings Inference". The catalog row uses account ID `683313688378` (different from the main `763104351884` used by most other DLCs). TEI is published from its own account namespace and th

Configuration goes in a `serving.properties` file packaged alongside the model artifacts (or the equivalent `OPTION_*` env vars) rather than `SM_VLLM_*`/`HF_MODEL_ID` — check the [DJL Serving docs](https://docs.djl.ai/master/docs/serving/in

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

"https://huggingface.co/api/datasets?filter=benchmark:official&limit=500" | jq '[.[] | {id, tags, description}]'

[Credential-related source omitted]

"https://huggingface.co/api/datasets/<namespace>/<repo>/leaderboard" | jq '[.[:15] | .[] | {rank, modelId, value, verified}]'

[Credential-related source omitted]

[Credential-related source omitted]

"https://huggingface.co/api/models/org/model1" | jq '{safetensors, tags, cardData}'

| # | Model | Params | [Benchmark 1] | [Benchmark 2] | License | On device | |---|-------|--------|--------------|--------------|---------|-----------| | ⭐1 | [org/name](https://huggingface.co/org/name) | 7B | 85.2% | — | Apache 2.0 | Yes (

|---|-------|--------|--------------|--------------|---------|-----------| | ⭐1 | [org/name](https://huggingface.co/org/name) | 7B | 85.2% | — | Apache 2.0 | Yes (fp16) | | 2 | [org/name](https://huggingface.co/org/name) | 13B | 83.1% | 71.

| ⭐1 | [org/name](https://huggingface.co/org/name) | 7B | 85.2% | — | Apache 2.0 | Yes (fp16) |

| 2 | [org/name](https://huggingface.co/org/name) | 13B | 83.1% | 71.5% | MIT | Q4 only |

| 3 | [org/name](https://huggingface.co/org/name) | 70B | 90.0% | 81.0% | Llama | Too large |

- Link model names to `https://huggingface.co/<model_id>`

If they say yes, ask whether they'd prefer to: - **Run locally** — ask about their device if not already known, then give appropriate setup instructions - **Run on HF Jobs** — point them to the HF Jobs guide: https://huggingface.co/docs/hug

- **Run on HF Jobs** — point them to the HF Jobs guide: https://huggingface.co/docs/huggingface_hub/en/guides/jobs

# Hugging Face Token (required for gated/private models) # Get your token at: https://huggingface.co/settings/tokens

# Get your token at: https://huggingface.co/settings/tokens

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

- Base URL: `https://datasets-server.huggingface.co`

curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=0&length=100"

curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=100&length=100"

- Create dataset repo in browser: `https://huggingface.co/new-dataset`

curl -s "https://datasets-server.huggingface.co/parquet?dataset=<namespace>/<repo>"

[Credential-related source omitted]

- [Quickstart](https://www.gradio.app/guides/quickstart)

- [The Interface Class](https://www.gradio.app/guides/the-interface-class)

- [Blocks and Event Listeners](https://www.gradio.app/guides/blocks-and-event-listeners)

- [Controlling Layout](https://www.gradio.app/guides/controlling-layout)

- [More Blocks Features](https://www.gradio.app/guides/more-blocks-features)

- [Custom CSS and JS](https://www.gradio.app/guides/custom-CSS-and-JS)

- [Streaming Outputs](https://www.gradio.app/guides/streaming-outputs)

- [Streaming Inputs](https://www.gradio.app/guides/streaming-inputs)

- [Sharing Your App](https://www.gradio.app/guides/sharing-your-app)

- [Custom HTML Components](https://www.gradio.app/guides/custom-HTML-components)

- [Getting Started with the Python Client](https://www.gradio.app/guides/getting-started-with-the-python-client)

- [Getting Started with the JS Client](https://www.gradio.app/guides/getting-started-with-the-js-client)

If a task requires significant customization of an existing component or a component that doesn't exist in Gradio, you can create one with `gr.HTML`. It supports `html_template` (with `${}` JS expressions and `{{}}` Handlebars syntax), `css

html_template = """         <h2>${label} rating:</h2>         ${Array.from({length: 5}, (_, i) => `<img class='${i < value ? '' : 'faded'}' src='https://upload.wikimedia.org/wikipedia/commons/d/df/Award-star-gold-3d.svg'>`).join('')}

<h2>${label} rating:</h2>         ${Array.from({length: 5}, (_, i) => `<img class='${i < value ? '' : 'faded'}' src='https://upload.wikimedia.org/wikipedia/commons/d/df/Award-star-gold-3d.svg'>`).join('')}         """

${Array.from({length: 5}, (_, i) => `<img class='${i < value ? '' : 'faded'}' src='https://upload.wikimedia.org/wikipedia/commons/d/df/Award-star-gold-3d.svg'>`).join('')}

hf_doc_search("your query", product="trl") hf_doc_fetch("https://huggingface.co/docs/trl/sft_trainer")  # SFT

hf_doc_fetch("https://huggingface.co/docs/trl/sft_trainer")  # SFT

hf_doc_fetch("https://huggingface.co/docs/trl/dpo_trainer")  # DPO

### ✅ **Account & Authentication** - Hugging Face Account with [Pro](https://hf.co/pro), [Team](https://hf.co/enterprise), or [Enterprise](https://hf.co/enterprise) plan (Jobs require paid plan)

- Hugging Face Account with [Pro](https://hf.co/pro), [Team](https://hf.co/enterprise), or [Enterprise](https://hf.co/enterprise) plan (Jobs require paid plan)

[Credential-related source omitted]

[Credential-related source omitted]

Job ID: abc123xyz Monitor: https://huggingface.co/jobs/username/abc123xyz

Monitor: https://huggingface.co/jobs/username/abc123xyz

[Credential-related source omitted]

# ✅ From Hugging Face Hub hf_jobs("uv", {"script": "https://huggingface.co/user/repo/resolve/main/train.py"})

hf_jobs("uv", {"script": "https://huggingface.co/user/repo/resolve/main/train.py"})

# ✅ From GitHub hf_jobs("uv", {"script": "https://raw.githubusercontent.com/user/repo/main/train.py"})

hf_jobs("uv", {"script": "https://raw.githubusercontent.com/user/repo/main/train.py"})

# ✅ From Gist hf_jobs("uv", {"script": "https://gist.githubusercontent.com/user/id/raw/train.py"})

hf_jobs("uv", {"script": "https://gist.githubusercontent.com/user/id/raw/train.py"})

hf repos create my-training-scripts --type model hf upload my-training-scripts ./train.py train.py # Use: https://huggingface.co/USERNAME/my-training-scripts/resolve/main/train.py

# Use: https://huggingface.co/USERNAME/my-training-scripts/resolve/main/train.py

hf_jobs("uv", {     "script": "https://github.com/huggingface/trl/blob/main/trl/scripts/sft.py",

"script": "https://github.com/huggingface/trl/blob/main/trl/scripts/sft.py",

[Credential-related source omitted]

**Benefits:** No code to write, maintained by TRL team, production-tested **When to use:** Standard TRL training, quick experiments, don't need custom code **Available:** Scripts are available from https://github.com/huggingface/trl/tree/ma

**Available:** Scripts are available from https://github.com/huggingface/trl/tree/main/examples/scripts

# ✅ CORRECT syntax - flags BEFORE script URL hf jobs uv run --flavor a10g-large --timeout 2h --secrets HF_TOKEN "https://example.com/train.py"

hf jobs uv run --flavor a10g-large --timeout 2h --secrets HF_TOKEN "https://example.com/train.py"

# ❌ WRONG - "run uv" instead of "uv run" hf jobs run uv "https://example.com/train.py" --flavor a10g-large

hf jobs run uv "https://example.com/train.py" --flavor a10g-large

# ❌ WRONG - flags AFTER script URL (will be ignored!) hf jobs uv run "https://example.com/train.py" --flavor a10g-large

hf jobs uv run "https://example.com/train.py" --flavor a10g-large

# ❌ WRONG - "--secret" instead of "--secrets" (plural) hf jobs uv run --secret HF_TOKEN "https://example.com/train.py"

hf jobs uv run --secret HF_TOKEN "https://example.com/train.py"

hf jobs uv run    --flavor a10g-large    --timeout 2h    --secrets HF_TOKEN    "https://huggingface.co/user/repo/resolve/main/train.py"

--timeout 2h \   --secrets HF_TOKEN \   "https://huggingface.co/user/repo/resolve/main/train.py"

"https://huggingface.co/user/repo/resolve/main/train.py"

**Benefits:** Pre-configured settings, automatic Trackio integration, automatic Hub push, one-line commands **When to use:** User working in terminal directly (not Claude Code context), quick local experimentation **Repository:** https://gi

**Repository:** https://github.com/huggingface/trl-jobs

[Credential-related source omitted]

hf_jobs("uv", {     "script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",

"script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",

# 1. Inspect dataset (costs ~$0.01, <1 min on CPU) hf_jobs("uv", {     "script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",

hf_jobs("uv", {     "script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",     "script_args": ["--dataset", "argilla/distilabel-math-preference-dpo", "--split", "train"]

"script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",

[Credential-related source omitted]

uv run https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py \

[Credential-related source omitted]

### External Scripts - [Dataset Inspector](https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py) - Validate dataset format before training (use via `uv run` or `hf_jobs`)

- [Dataset Inspector](https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py) - Validate dataset format before training (use via `uv run` or `hf_jobs`)

### External Links - [TRL Documentation](https://huggingface.co/docs/trl)

- [TRL Documentation](https://huggingface.co/docs/trl)

- [TRL Jobs Training Guide](https://huggingface.co/docs/trl/en/jobs_training)

- [TRL Jobs Package](https://github.com/huggingface/trl-jobs)

- [HF Jobs Documentation](https://huggingface.co/docs/huggingface_hub/guides/jobs)

- [TRL Example Scripts](https://github.com/huggingface/trl/tree/main/examples/scripts)

- [UV Scripts Guide](https://docs.astral.sh/uv/guides/scripts/)

- [UV Scripts Organization](https://huggingface.co/uv-scripts)

[Credential-related source omitted]

- Ensure llama.cpp supports the model architecture - Check for standard architecture (Qwen, Llama, Mistral, etc.) - Update llama.cpp to latest: `git clone --depth 1 https://github.com/ggerganov/llama.cpp.git`

- Check for standard architecture (Qwen, Llama, Mistral, etc.) - Update llama.cpp to latest: `git clone --depth 1 https://github.com/ggerganov/llama.cpp.git` - Check llama.cpp documentation for model support

- Update llama.cpp to latest: `git clone --depth 1 https://github.com/ggerganov/llama.cpp.git`

**External:** - [llama.cpp Repository](https://github.com/ggerganov/llama.cpp)

- [llama.cpp Repository](https://github.com/ggerganov/llama.cpp)

- [GGUF Specification](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md)

- [Ollama Documentation](https://ollama.ai)

- [LM Studio](https://lmstudio.ai)

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

print("✅ Model saved to: https://huggingface.co/myusername/my-trained-model")

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

**Possible causes:** 1. Repository is private—check https://huggingface.co/username

1. Repository is private—check https://huggingface.co/username

[Credential-related source omitted]

print("✅ Training complete!") print(f"Model available at: https://huggingface.co/myusername/qwen-capybara-sft")

print(f"Model available at: https://huggingface.co/myusername/qwen-capybara-sft")

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[MLX](https://github.com/ml-explore/mlx) offers tighter Apple Silicon integration but has a smaller ecosystem and less mature training APIs. For this skill's workflow (local validation → HF Jobs), PyTorch + MPS is recommended for consistenc

# Check script/file paths (for URL-based scripts) # Verify before using: https://github.com/user/repo/blob/main/script.py

# Verify before using: https://github.com/user/repo/blob/main/script.py

# ❌ INCOMPLETE: Assumes build tools exist subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"])

subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"])

subprocess.run(["apt-get", "update", "-qq"], check=True) subprocess.run(["apt-get", "install", "-y", "-qq", "build-essential", "cmake"], check=True) subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.c

subprocess.run(["apt-get", "install", "-y", "-qq", "build-essential", "cmake"], check=True) subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"]) # ... then build

subprocess.run(["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"])

**Option B: Create manually** - Create Space via Hub UI at https://huggingface.co/new-space

- Create Space via Hub UI at https://huggingface.co/new-space

[Credential-related source omitted]

[Credential-related source omitted]

After starting training: 1. Navigate to the Space: `https://huggingface.co/spaces/username/trackio`

1. Navigate to the Space: `https://huggingface.co/spaces/username/trackio`

**Documentation:** `hf_doc_fetch("https://huggingface.co/docs/trl/sft_trainer")`

**Documentation:** `hf_doc_fetch("https://huggingface.co/docs/trl/dpo_trainer")`

# Use TRL maintained script hf_jobs("uv", {     "script": "https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py",

hf_jobs("uv", {     "script": "https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py",     "script_args": [

"script": "https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py",

[Credential-related source omitted]

**Documentation:** `hf_doc_fetch("https://huggingface.co/docs/trl/grpo_trainer")`

**Documentation:** `hf_doc_fetch("https://huggingface.co/docs/trl/reward_trainer")`

hf_doc_fetch("https://huggingface.co/docs/trl/dataset_formats")

uv run https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py \

- `scripts/train_sft_example.py` - Complete SFT template - `scripts/train_dpo_example.py` - Complete DPO template - [Dataset Inspector](https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py) - Dataset format validat

- [Dataset Inspector](https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py) - Dataset format validation tool

[Credential-related source omitted]

[Credential-related source omitted]

**For DPO documentation:** Use `hf_doc_fetch("https://huggingface.co/docs/trl/dpo_trainer")`

hf_jobs("uv", {     "script": "https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py",

"script": "https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py",

[Credential-related source omitted]

**For GRPO documentation:** Use `hf_doc_fetch("https://huggingface.co/docs/trl/grpo_trainer")`

[Credential-related source omitted]

[Credential-related source omitted]

- [ ] User has write access to target repo - [ ] Token has write permissions (check at https://huggingface.co/settings/tokens) - [ ] Training script calls `trainer.push_to_hub()` at the end

- [ ] Token has write permissions (check at https://huggingface.co/settings/tokens)

hf_doc_fetch("https://huggingface.co/docs/trl/dataset_formats")

uv run https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py \

hf_jobs("uv", {        "script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",

"script": "https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py",

2. **Check token permissions:**    - Go to https://huggingface.co/settings/tokens

- Go to https://huggingface.co/settings/tokens

[Credential-related source omitted]

**Solutions:** - Check Jobs dashboard for status: https://huggingface.co/jobs

- Check Jobs dashboard for status: https://huggingface.co/jobs

hf_doc_fetch("https://huggingface.co/docs/huggingface_hub/guides/jobs")

4. **Ask in HF forums:** https://discuss.huggingface.co/

- **GitHub**: [unslothai/unsloth](https://github.com/unslothai/unsloth)

- **Docs**: [unsloth.ai/docs](https://unsloth.ai/docs)

[Credential-related source omitted]

- `scripts/unsloth_sft_example.py` - Complete text LLM training example - [Unsloth Documentation](https://unsloth.ai/docs)

- [Unsloth Documentation](https://unsloth.ai/docs)

- [LFM2.5 Guide](https://unsloth.ai/docs/models/tutorials/lfm2.5)

- [Qwen3-VL Guide](https://unsloth.ai/docs/models/qwen3-vl-how-to-run-and-fine-tune)

- [Unsloth GitHub](https://github.com/unslothai/unsloth)

#!/usr/bin/env python3

- Ubuntu/Debian: sudo apt-get update && sudo apt-get install -y build-essential cmake

- RHEL/CentOS: sudo yum groupinstall -y "Development Tools" && sudo yum install -y cmake

print("     Ubuntu/Debian: sudo apt-get install git")

print("     RHEL/CentOS: sudo yum install git")

print("     Ubuntu/Debian: sudo apt-get install build-essential cmake")

print("     RHEL/CentOS: sudo yum groupinstall 'Development Tools' && sudo yum install cmake")

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

if not run_command(     ["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"],

["git", "clone", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"],

if not run_command(         ["git", "clone", "--depth", "1", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"],

["git", "clone", "--depth", "1", "https://github.com/ggerganov/llama.cpp.git", "/tmp/llama.cpp"],

This is a GGUF conversion of [{ADAPTER_MODEL}](https://huggingface.co/{ADAPTER_MODEL}), which is a LoRA fine-tuned version of [{BASE_MODEL}](https://huggingface.co/{BASE_MODEL}).

year = {{2025}},   publisher = {{Hugging Face}},   url = {{https://huggingface.co/{OUTPUT_REPO}}}

publisher = {{Hugging Face}},   url = {{https://huggingface.co/{OUTPUT_REPO}}} }}

url = {{https://huggingface.co/{OUTPUT_REPO}}}

print("\n" + "=" * 60) print("✅ GGUF Conversion Complete!") print(f"📦 Repository: https://huggingface.co/{OUTPUT_REPO}")

print("✅ GGUF Conversion Complete!") print(f"📦 Repository: https://huggingface.co/{OUTPUT_REPO}") print(f"\n📥 Download with:")

print(f"📦 Repository: https://huggingface.co/{OUTPUT_REPO}") print(f"\n📥 Download with:") print(f"   hf download {OUTPUT_REPO} {model_name}-q4_k_m.gguf")

#!/usr/bin/env python3

Usage with HF Jobs:     hf_jobs("uv", {         "script": "https://huggingface.co/datasets/evalstate/trl-helpers/raw/main/dataset_inspector.py",

hf_jobs("uv", {         "script": "https://huggingface.co/datasets/evalstate/trl-helpers/raw/main/dataset_inspector.py",         "script_args": ["--dataset", "your/dataset", "--split", "train"]

"script": "https://huggingface.co/datasets/evalstate/trl-helpers/raw/main/dataset_inspector.py",

parser.add_argument("--config", type=str, default="default", help="Dataset config name (default: default)")     parser.add_argument("--preview", type=int, default=150, help="Max chars per field preview")     parser.add_argument("--samples",

parser.add_argument("--preview", type=int, default=150, help="Max chars per field preview")     parser.add_argument("--samples", type=int, default=5, help="Number of samples to fetch (default: 5)")     parser.add_argument("--json-output", a

parser.add_argument("--samples", type=int, default=5, help="Number of samples to fetch (default: 5)")

try:         with urllib.request.urlopen(url, timeout=10) as response:

with urllib.request.urlopen(url, timeout=10) as response:

url = f"https://datasets-server.huggingface.co/splits?dataset={urllib.parse.quote(dataset)}"

url = f"https://datasets-server.huggingface.co/rows?dataset={urllib.parse.quote(dataset)}&config={config}&split={split}&offset={offset}&length={length}"

#!/usr/bin/env python3

[Credential-related source omitted]

#!/usr/bin/env -S uv run --script

BASE_URL = "https://huggingface.co"

[Credential-related source omitted]

req = urllib.request.Request(url, headers=auth_headers())

try:         with urllib.request.urlopen(req, timeout=DEFAULT_TIMEOUT) as resp:             return json.loads(resp.read().decode("utf-8"))

with urllib.request.urlopen(req, timeout=DEFAULT_TIMEOUT) as resp:

#!/usr/bin/env python3

[Credential-related source omitted]

print("✅ Complete! Model at: https://huggingface.co/username/qwen-dpo-aligned")

print("📊 View metrics at: https://huggingface.co/spaces/username/trackio")

#!/usr/bin/env python3

[Credential-related source omitted]

Note: For most GRPO use cases, the TRL maintained script is recommended:     https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py

https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py

print("✅ Complete! Model at: https://huggingface.co/username/qwen-grpo-math")

print("📊 View metrics at: https://huggingface.co/spaces/username/trackio")

#!/usr/bin/env python3

[Credential-related source omitted]

print("✅ Complete! Model at: https://huggingface.co/username/qwen-capybara-sft")

print("📊 View metrics at: https://huggingface.co/spaces/username/trackio")

Executable file

[Credential-related source omitted]

if args.trackio_space:         os.environ["TRACKIO_SPACE_ID"] = args.trackio_space         logger.info(f"Trackio dashboard: https://huggingface.co/spaces/{args.trackio_space}")

[Credential-related source omitted]

logger.info(f"Trackio dashboard: https://huggingface.co/spaces/{args.trackio_space}")

[Credential-related source omitted]

save_method="merged_16bit",         )         print(f"Merged model available at: https://huggingface.co/{args.output_repo}")

)         print(f"Merged model available at: https://huggingface.co/{args.output_repo}")     else:

print(f"Merged model available at: https://huggingface.co/{args.output_repo}")

print(f"\nPushing adapter to {args.output_repo}...")         model.push_to_hub(args.output_repo, tokenizer=tokenizer)         print(f"Adapter available at: https://huggingface.co/{args.output_repo}")

print(f"Adapter available at: https://huggingface.co/{args.output_repo}")

1. Search the Hub with `apps=llama.cpp`. 2. Open `https://huggingface.co/<repo>?local-app=llama.cpp`.

2. Open `https://huggingface.co/<repo>?local-app=llama.cpp`.

3. Prefer the exact HF local-app snippet and quant recommendation when it is visible. 4. Confirm exact `.gguf` filenames with `https://huggingface.co/api/models/<repo>/tree/main?recursive=true`. 5. Launch with `llama-cli -hf <repo>:<QUANT>`

4. Confirm exact `.gguf` filenames with `https://huggingface.co/api/models/<repo>/tree/main?recursive=true`.

git clone https://github.com/ggml-org/llama.cpp

https://huggingface.co/models?apps=llama.cpp&sort=trending

https://huggingface.co/models?search=Qwen3.6&apps=llama.cpp&sort=trending

https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending

curl http://localhost:8080/v1/chat/completions \

- llama.cpp: `https://github.com/ggml-org/llama.cpp`

- Hugging Face GGUF + llama.cpp docs: `https://huggingface.co/docs/hub/gguf-llamacpp`

- Hugging Face Local Apps docs: `https://huggingface.co/docs/hub/main/local-apps`

- Hugging Face Local Agents docs: `https://huggingface.co/docs/hub/agents-local`

- GGUF converter Space: `https://huggingface.co/spaces/ggml-org/gguf-my-repo`

Search: https://huggingface.co/models?apps=llama.cpp&sort=trending

https://huggingface.co/models?apps=llama.cpp&sort=trending

Search with text: https://huggingface.co/models?search=<term>&apps=llama.cpp&sort=trending

https://huggingface.co/models?search=<term>&apps=llama.cpp&sort=trending

Search with size bounds: https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending

https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending

Repo local-app view: https://huggingface.co/<repo>?local-app=llama.cpp

https://huggingface.co/<repo>?local-app=llama.cpp

Repo tree API: https://huggingface.co/api/models/<repo>/tree/main?recursive=true

https://huggingface.co/api/models/<repo>/tree/main?recursive=true

Repo file tree: https://huggingface.co/<repo>/tree/main

https://huggingface.co/<repo>/tree/main

Example: https://huggingface.co/models?search=Qwen&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending

https://huggingface.co/<repo>?local-app=llama.cpp

https://huggingface.co/api/models/<repo>/tree/main?recursive=true

Use `https://huggingface.co/<repo>/tree/main` only as a human fallback if the API endpoint fails or the user wants the web view.

https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF?local-app=llama.cpp

https://huggingface.co/api/models/unsloth/Qwen3.6-35B-A3B-GGUF/tree/main?recursive=true

https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF/tree/main

https://huggingface.co/<repo>?local-app=llama.cpp

https://huggingface.co/api/models/<repo>/tree/main?recursive=true

https://huggingface.co/models?apps=llama.cpp&sort=trending

https://huggingface.co/models?search=<term>&apps=llama.cpp&sort=trending

https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending

https://huggingface.co/<repo>?local-app=llama.cpp

https://huggingface.co/api/models/<repo>/tree/main?recursive=true

> I need a Hugging Face access token with **write** scope (to read the LoRA if it's private/gated, and to publish the Space). Create one at https://huggingface.co/settings/tokens. Paste it here.

**Gradio component freshness.** Gradio's component set evolves. Before defaulting to plain components, consider whether something newer fits better — for example `gr.ImageSlider` for before/after on edit LoRAs, `gr.BrowserState` for persist

**`gr.Examples` for media-input Spaces.** When no fitting example media is available from the model's own repo, pull from the shared input pools — split by modality so the HF dataset viewer can render proper thumbnails: images at [`linoyts/

[Credential-related source omitted]

2. **What the base-model reference's "Required dependencies" subsection says.** Each base-model file lists the non-obvious extras the pipeline pulls in — `torchvision` for Qwen-Image (Qwen 2.5-VL text encoder), `imageio[ffmpeg]` for LTX (vi

4. **The diffusers/ML stack:** `diffusers`, `transformers`, `accelerate`, `peft`, `safetensors`. Default to plain (unpinned). Switch `diffusers` to `git+https://github.com/huggingface/diffusers` if the base-model reference says the model ne

- `sdk: gradio` — required for ZeroGPU. - `sdk_version` — match the Gradio version you wrote against. Look up the current version (`pip index versions gradio`, or check https://www.gradio.app) rather than guessing.

- `sdk_version` — match the Gradio version you wrote against. Look up the current version (`pip index versions gradio`, or check https://www.gradio.app) rather than guessing.

- `hardware: zero-a10g` — the legacy string for ZeroGPU. The actual hardware is NVIDIA RTX Pro 6000 Blackwell, but the identifier is `zero-a10g`. ZeroGPU is available to PRO, Team, and Enterprise accounts; if the user isn't subscribed, the 

- `short_description` — appears on the Space tile. **Keep it short (~60 characters or less).** The Hub's YAML validator rejects long values with a 400 from `https://huggingface.co/api/validate-yaml`, which surfaces as an `HfHubHTTPError` du

[Credential-related source omitted]

**After upload**, run the smoke-test below before sharing — the build runs asynchronously and silent failures (wrong `weight_name`, missing dep, wrong pipeline class) only surface at first inference. **Once the smoke-test passes**, share th

- **`HfHubHTTPError: 400 Bad Request` from `https://huggingface.co/api/validate-yaml`** during `create_repo` or `upload_file`. The README YAML failed server-side validation. By far the most common cause is a `short_description` that's too l

- **403 on `create_repo`** with `space_hardware="zero-a10g"`: user isn't on PRO/Team/Enterprise, so they can't request ZeroGPU at creation time. Fix: retry `create_repo` without `space_hardware`, leave `hardware: zero-a10g` in the README YA

if stage == "RUNNING": break     if stage in {"BUILD_ERROR", "RUNTIME_ERROR", "CONFIG_ERROR"}:         raise RuntimeError(f"Build failed: {stage}. Logs: https://huggingface.co/spaces/{repo_id}/logs/container")

if stage in {"BUILD_ERROR", "RUNTIME_ERROR", "CONFIG_ERROR"}:         raise RuntimeError(f"Build failed: {stage}. Logs: https://huggingface.co/spaces/{repo_id}/logs/container")     time.sleep(15)

raise RuntimeError(f"Build failed: {stage}. Logs: https://huggingface.co/spaces/{repo_id}/logs/container")

If the build fails, fetch the container logs (`https://huggingface.co/spaces/{repo_id}/logs/container`), read the traceback, and propose a fix. Don't run `gradio info` against a Space that isn't running — it'll hang or 503.

[Credential-related source omitted]

[Credential-related source omitted]

- **HTTPError 503 / "Space is sleeping"** → the Space spun down between steps 1 and 3. Wake it (`api.restart_space(repo_id)`) and retry. - **Inference error mentioning `weight_name` / `safetensors`** → the LoRA filename in `app.py` doesn't 

- **Inference error mentioning `weight_name` / `safetensors`** → the LoRA filename in `app.py` doesn't match the actual file in the LoRA repo. Re-check `list_repo_files`, fix `weight_name=`, re-upload `app.py`. - **Inference error mentionin

- **Inference error mentioning a missing pipeline class or attribute** → diffusers version too old. Switch `requirements.txt` to `git+https://github.com/huggingface/diffusers` and re-upload.

| Repo | Role | Use it for | |------|------|------------| | [`krea/Krea-2-Turbo`](https://huggingface.co/krea/Krea-2-Turbo) | 8-step **distilled** | **Inference / demos** |

|------|------|------------| | [`krea/Krea-2-Turbo`](https://huggingface.co/krea/Krea-2-Turbo) | 8-step **distilled** | **Inference / demos** | | [`krea/Krea-2-Raw`](https://huggingface.co/krea/Krea-2-Raw) | base, non-distilled | **LoRA tra

| [`krea/Krea-2-Turbo`](https://huggingface.co/krea/Krea-2-Turbo) | 8-step **distilled** | **Inference / demos** |

| [`krea/Krea-2-Raw`](https://huggingface.co/krea/Krea-2-Raw) | base, non-distilled | **LoRA training** — *not* for inference |

| `Lightricks/LTX-Video` (0.9.x) | Yes — `LTXPipeline`, `LTXImageToVideoPipeline`, `LTXConditionPipeline` | Yes | | `Lightricks/LTX-2`        | Yes — `LTX2Pipeline` from `diffusers.pipelines.ltx2` | Yes (recent diffusers) | | `Lightricks/LT

| `Lightricks/LTX-2.3`      | Partial — diffusers support is still limited overall, so the original `Lightricks/LTX-2.3` repo can still be used via the native path. Diffusers-converted variants exist at `dg845/LTX-2.3-Diffusers` and `dg845/

git+https://github.com/huggingface/diffusers

git+https://github.com/Lightricks/LTX-Video.git

# in requirements.txt git+https://github.com/Lightricks/LTX-Video.git

git+https://github.com/Lightricks/LTX-Video.git

- **Latest pipelines often need git diffusers.** Pin to `git+https://github.com/huggingface/diffusers` in `requirements.txt` for any LTX variant released in the last few weeks.

- **`git+diffusers` is a moving target — verify LTX2 output quality.** Bare `@main` inherits whatever's there. The LTX2 text connector carried a token-reversal regression (PR #13564) that scrambled prompt tokens/registers — degrading prompt

git+https://github.com/huggingface/diffusers

- `gr.HTML` — https://www.gradio.app/docs/gradio/html

- Custom components — https://www.gradio.app/guides/custom-components-in-five-minutes

- `Blocks.launch(head=, css=)` — https://www.gradio.app/docs/gradio/blocks#blocks-launch

head = '<script src="https://cdnjs.cloudflare.com/ajax/libs/three.js/r128/three.min.js"></script>'

- **3D camera control via Three.js** (Approach B, `gr.HTML` subclass): https://huggingface.co/spaces/multimodalart/qwen-image-multiple-angles-3d-camera

- **Bounding-box drag/resize via canvas** (Approach A, hidden inputs + custom Run button): https://huggingface.co/spaces/linoyts/FLUX.2-klein-Move

Browse the rest at https://www.gradio.app/custom-components/gallery before going further down the ladder.

Before defaulting to a plain component or guessing at a custom one, web-fetch the current Gradio docs at https://www.gradio.app/docs.

**ZeroGPU requires PRO/Team/Enterprise.** A free-tier user can create a Space with `hardware: zero-a10g` in the README, but it'll fall back to CPU. If the user isn't on a supporting plan, mention this and point them at two paths: upgrade to

- **User already authenticated and the LoRA repo is public**: use the existing token. Confirm the username with the user before publishing ("I'll publish to `{username}` — confirm?"). - **User already authenticated and the LoRA repo is priv

- **No cached token**: ask the user. One ask, with the explanation: "I need a Hugging Face access token with **write** scope. Create one at https://huggingface.co/settings/tokens. Paste it here." The same token will be reused for publishing

[Credential-related source omitted]

[Credential-related source omitted]

If `create_repo` rejects the hardware (typically because the user isn't on PRO), retry without `space_hardware=`, set the README's `hardware: zero-a10g` anyway, and tell the user the Space will run on CPU until they either upgrade to PRO or

The Space URL is `https://huggingface.co/spaces/{repo_id}`. Build logs are at `https://huggingface.co/spaces/{repo_id}/logs/container`. Runtime logs at `https://huggingface.co/spaces/{repo_id}/logs/run`.

- **`HfHubHTTPError: 400 Bad Request` from `https://huggingface.co/api/validate-yaml`.** The README's YAML frontmatter failed server-side validation. By far the most common cause is `short_description` exceeding the server's length cap (the

- **`HfHubHTTPError: 403 Forbidden` on `create_repo` with `space_hardware="zero-a10g"`.** The user's account can't request ZeroGPU at creation time (typically because they're not on PRO/Team/Enterprise). Fix: retry `create_repo` without the

- **`weight_name` mismatch in `load_lora_weights`.** The actual file in the repo is named differently. Fix: `api.list_repo_files(repo_id)` to find the real filename; pass `weight_name=` explicitly. - **Gated base model, no token.** The base

- **Gated base model, no token.** The base model (e.g. `black-forest-labs/FLUX.1-dev`) requires accepting a license. Fix: ensure the user has accepted the license on the Hub, and the token is set as a Space secret. - **Diffusers version too

- **Diffusers version too old for the pipeline class.** The base model was released after the latest pinned diffusers. Fix: change `requirements.txt` from `diffusers` to `git+https://github.com/huggingface/diffusers`.

**Direct URL Access:** You can also visit `https://huggingface.co/papers/{arxiv-id}` directly to index a paper.

You can also visit `https://huggingface.co/papers/{arxiv-id}` directly to index a paper.

**Manual Process:** 1. Navigate to your paper's page: `https://huggingface.co/papers/{arxiv-id}`

1. Navigate to your paper's page: `https://huggingface.co/papers/{arxiv-id}`

This model is based on the approach described in [Our Paper](https://arxiv.org/abs/2301.12345).

Dataset introduced in [Our Paper](https://arxiv.org/abs/2301.12345).

For more details, see the [paper page](https://huggingface.co/papers/2301.12345).

- **Hugging Face Paper Pages**: [hf.co/papers](https://huggingface.co/papers)

- **Model Cards Guide**: [hf.co/docs/hub/model-cards](https://huggingface.co/docs/hub/en/model-cards)

- **Dataset Cards Guide**: [hf.co/docs/hub/datasets-cards](https://huggingface.co/docs/hub/en/datasets-cards)

- **Research Article Template**: [tfrere/research-article-template](https://huggingface.co/spaces/tfrere/research-article-template)

- **arXiv Format Guide**: [arxiv.org/help/submit](https://arxiv.org/help/submit)

This skill complements [tfrere's research article template](https://huggingface.co/spaces/tfrere/research-article-template) by providing:

{   "exists": true,   "url": "https://huggingface.co/papers/2301.12345",

"exists": true,   "url": "https://huggingface.co/papers/2301.12345",   "arxiv_id": "2301.12345",

"url": "https://huggingface.co/papers/2301.12345",

"arxiv_id": "2301.12345",   "arxiv_url": "https://arxiv.org/abs/2301.12345" }

"arxiv_url": "https://arxiv.org/abs/2301.12345"

This skill complements [tfrere's research article template](https://huggingface.co/spaces/tfrere/research-article-template):

# 1. Use tfrere's Space to create a beautiful web-based paper # Visit: https://huggingface.co/spaces/tfrere/research-article-template

# Visit: https://huggingface.co/spaces/tfrere/research-article-template

# Visit the URL directly to trigger indexing open "https://huggingface.co/papers/2301.12345"

open "https://huggingface.co/papers/2301.12345"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

uv run scripts/paper_manager.py check --arxiv-id "2301.12345" uv run scripts/paper_manager.py check --arxiv-id "arxiv:2301.12345" uv run scripts/paper_manager.py check --arxiv-id "https://arxiv.org/abs/2301.12345"

uv run scripts/paper_manager.py check --arxiv-id "https://arxiv.org/abs/2301.12345"

- Explore the [Paper Pages documentation](https://huggingface.co/docs/hub/en/paper-pages)

- Check out [tfrere's research template](https://huggingface.co/spaces/tfrere/research-article-template)

- Browse [papers on HF](https://huggingface.co/papers)

- Learn about [model cards](https://huggingface.co/docs/hub/en/model-cards)

### Hugging Face Paper Pages - View paper: `https://huggingface.co/papers/{arxiv-id}`

- View paper: `https://huggingface.co/papers/{arxiv-id}`

- Example: `https://huggingface.co/papers/2301.12345`

### arXiv - Abstract: `https://arxiv.org/abs/{arxiv-id}`

- Abstract: `https://arxiv.org/abs/{arxiv-id}`

- PDF: `https://arxiv.org/pdf/{arxiv-id}.pdf`

- Example: `https://arxiv.org/abs/2301.12345`

- `2301.12345` - `arxiv:2301.12345` - `https://arxiv.org/abs/2301.12345`

- `arxiv:2301.12345` - `https://arxiv.org/abs/2301.12345` - `https://arxiv.org/pdf/2301.12345.pdf`

- `https://arxiv.org/abs/2301.12345`

- `https://arxiv.org/pdf/2301.12345.pdf`

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

### Paper not found Visit `https://huggingface.co/papers/{arxiv-id}` to trigger indexing

Visit `https://huggingface.co/papers/{arxiv-id}` to trigger indexing

- [Full documentation](../SKILL.md) - [Usage examples](../examples/example_usage.md) - [HF Paper Pages](https://huggingface.co/papers)

- [Usage examples](../examples/example_usage.md) - [HF Paper Pages](https://huggingface.co/papers) - [tfrere's template](https://huggingface.co/spaces/tfrere/research-article-template)

- [HF Paper Pages](https://huggingface.co/papers)

- [tfrere's template](https://huggingface.co/spaces/tfrere/research-article-template)

#!/usr/bin/env -S uv run

[Credential-related source omitted]

paper_url = f"https://huggingface.co/papers/{arxiv_id}"

try:             response = requests.get(paper_url, timeout=10)

response = requests.get(paper_url, timeout=10)

except ValueError as e:             return {"exists": False, "error": str(e)}         paper_url = f"https://huggingface.co/papers/{arxiv_id}"

paper_url = f"https://huggingface.co/papers/{arxiv_id}"

try:             response = requests.get(paper_url, timeout=10)

response = requests.get(paper_url, timeout=10)

"url": paper_url,                     "arxiv_id": arxiv_id,                     "arxiv_url": f"https://arxiv.org/abs/{arxiv_id}"

"arxiv_id": arxiv_id,                     "arxiv_url": f"https://arxiv.org/abs/{arxiv_id}"                 }

"arxiv_url": f"https://arxiv.org/abs/{arxiv_id}"

paper_url = f"https://huggingface.co/papers/{arxiv_id}"

repo_url = f"https://huggingface.co/{repo_id}"

arxiv_url = f"https://arxiv.org/abs/{arxiv_id}"

hf_paper_url = f"https://huggingface.co/papers/{arxiv_id}"

except ValueError as e:             return {"error": str(e)}         api_url = f"https://export.arxiv.org/api/query?id_list={arxiv_id}"

api_url = f"https://export.arxiv.org/api/query?id_list={arxiv_id}"

try:             response = requests.get(api_url, timeout=10)

response = requests.get(api_url, timeout=10)

"authors": [self._sanitize_text(a) for a in raw_authors],                 "abstract": self._sanitize_text(raw_abstract) if raw_abstract else None,                 "arxiv_url": f"https://arxiv.org/abs/{arxiv_id}",

"abstract": self._sanitize_text(raw_abstract) if raw_abstract else None,                 "arxiv_url": f"https://arxiv.org/abs/{arxiv_id}",                 "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf"

"arxiv_url": f"https://arxiv.org/abs/{arxiv_id}",

"pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf"

text = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f\x7f]', '', text)

print(f"Searching for: {args.query}")         print("Search functionality coming soon!")         print(f"Visit: https://huggingface.co/papers?search={args.query}")

print(f"Visit: https://huggingface.co/papers?search={args.query}")

- User shares a Hugging Face paper page URL (e.g. `https://huggingface.co/papers/2602.08025`)

- User shares a Hugging Face markdown paper page URL (e.g. `https://huggingface.co/papers/2602.08025.md`)

- User shares an arXiv URL (e.g. `https://arxiv.org/abs/2602.08025` or  `https://arxiv.org/pdf/2602.08025`)

| Input | Paper ID | | --- | --- | | `https://huggingface.co/papers/2602.08025` | `2602.08025` |

| --- | --- | | `https://huggingface.co/papers/2602.08025` | `2602.08025` | | `https://huggingface.co/papers/2602.08025.md` | `2602.08025` |

| `https://huggingface.co/papers/2602.08025` | `2602.08025` |

| `https://huggingface.co/papers/2602.08025.md` | `2602.08025` |

| `https://arxiv.org/abs/2602.08025` | `2602.08025` |

| `https://arxiv.org/pdf/2602.08025` | `2602.08025` |

curl -s "https://huggingface.co/papers/{PAPER_ID}.md"

This should return the Hugging Face paper page as markdown. This relies on the HTML version of the paper at https://arxiv.org/html/{PAPER_ID}.

curl -s -H "Accept: text/markdown" "https://huggingface.co/papers/{PAPER_ID}"

All endpoints use the base URL `https://huggingface.co`.

curl -s "https://huggingface.co/api/papers/{PAPER_ID}"

curl https://huggingface.co/api/models?filter=arxiv:{PAPER_ID}

curl https://huggingface.co/api/datasets?filter=arxiv:{PAPER_ID}

curl https://huggingface.co/api/spaces?filter=arxiv:{PAPER_ID}

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

"https://huggingface.co/api/daily_papers?p=0&limit=20&date=2017-07-21&sort=publishedAt"

[Credential-related source omitted]

[Credential-related source omitted]

"https://huggingface.co/api/papers?cursor={CURSOR}&limit=20"

[Credential-related source omitted]

[Credential-related source omitted]

"https://huggingface.co/api/papers/search?q=vision+language&limit=20"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

"projectPage": "https://example.com",

"githubRepo": "https://github.com/org/repo",

- **404 on `https://huggingface.co/papers/{PAPER_ID}` or `md` endpoint**: the paper is not indexed on Hugging Face paper pages yet.

- Check the regular paper page at `https://huggingface.co/papers/{PAPER_ID}`

- Fall back to the arXiv page or PDF for the original source:   - `https://arxiv.org/abs/{PAPER_ID}`   - `https://arxiv.org/pdf/{PAPER_ID}`

- `https://arxiv.org/abs/{PAPER_ID}`

- `https://arxiv.org/pdf/{PAPER_ID}`

[Credential-related source omitted]

To add the Hugging Face Space creation skill for your agent, [Install the hf CLI](https://huggingface.co/docs/huggingface_hub/guides/cli#getting-started), login with `hf auth login` and run

Or just point your agent here https://github.com/huggingface/skills/tree/main/skills/huggingface-spaces and it will know what to do

1. Check the `hf` CLI is installed: `which hf`. If not, `pip install -U huggingface_hub`. 2. Check the user is logged in: `hf auth whoami`. If not, run `hf auth login` — it prints a URL and a one-time code; ask the user to open the URL and 

2. Check the user is logged in: `hf auth whoami`. If not, run `hf auth login` — it prints a URL and a one-time code; ask the user to open the URL and enter the code, then login completes automatically (OAuth, no token needed). Alternatively

- **Gradio** — most Spaces. Python, fast iteration, supports ZeroGPU. - **Docker** — arbitrary container. Use when you need a non-Python stack or a pre-built template (Streamlit, Argilla, Shiny, etc. — full list at https://huggingface.co/do

- **Docker** — arbitrary container. Use when you need a non-Python stack or a pre-built template (Streamlit, Argilla, Shiny, etc. — full list at https://huggingface.co/docs/hub/spaces-sdks-docker). Does **not** support ZeroGPU.

For the authoritative reference: https://huggingface.co/docs/hub/spaces-overview

The Space now exists at `https://huggingface.co/spaces/<namespace>/<name>` but is empty.

All frontmatter options: https://huggingface.co/docs/hub/spaces-config-reference

- **Do list if you use them**: `torchvision`, `torchaudio` (not preinstalled), plus everything else (`diffusers`, `transformers`, `accelerate`, `sentencepiece`, …). - ZeroGPU only accepts torch `2.8.0`, `2.9.1`, `2.10.0`, `2.11.0`. Default 

- For prebuilt CUDA-extension wheels (`flash_attn`, `xformers`, `pytorch3d`, `nvdiffrast`, `diff_gaussian_rasterization`, `torchmcubes`): use the prebuilt Blackwell wheels at `https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-

- **Gradio patterns** (themes, `gr.Examples`, streaming, custom HTML components, `gr.Server`): [`references/gradio.md`](references/gradio.md). - **Docker**: https://huggingface.co/docs/hub/spaces-sdks-docker. Examples: `hf spaces list --fil

- **Docker**: https://huggingface.co/docs/hub/spaces-sdks-docker. Examples: `hf spaces list --filter docker`.

- **Static**: https://huggingface.co/docs/hub/spaces-sdks-static. For built SPAs, set `app_build_command: npm run build` and `app_file: dist/index.html` in frontmatter.

[Credential-related source omitted]

hf jobs run --flavor rtx-pro-6000 --timeout 30m --secrets HF_TOKEN       pytorch/pytorch:2.11.0-cuda13.0-cudnn9-devel       bash -c 'export TORCH_CUDA_ARCH_LIST="12.0+PTX" &&                pip wheel --no-build-isolation --no-deps          

bash -c 'export TORCH_CUDA_ARCH_LIST="12.0+PTX" && \               pip wheel --no-build-isolation --no-deps \                   git+https://github.com/<org>/<extension>.git -w /tmp/wheels && \

pip wheel --no-build-isolation --no-deps \                   git+https://github.com/<org>/<extension>.git -w /tmp/wheels && \               pip install -U huggingface_hub && \

git+https://github.com/<org>/<extension>.git -w /tmp/wheels && \

Then reference `https://huggingface.co/datasets/<user>/zerogpu-wheels/resolve/main/wheels/<file>.whl` in requirements.txt, or download and commit the wheel to the Space (Strategy 2). Three things to line up: the image's **torch + CUDA** mus

[Credential-related source omitted]

Either way, **fetch the official Space's live files first** (`https://huggingface.co/spaces/{id}/raw/main/{path}`) and treat them — not the reference files' pins — as source of truth. The reference files record what shipped as of mid-2026; 

**Shape B — a real rasterizer (only for server-rendered orbit videos).** If the code uses the upstream Inria API, take the prebuilt wheel from `requirements.md`'s dataset and be done. `ashawkey/LGM` needs its fork, so its Space JIT-builds i

- **TripoSplat** — the current default pick: MIT, running official ZeroGPU Space, fp16 weights well within 48 GB, ~262k gaussians per generation, BiRefNet background removal built in. Caveat when duplicating: the official Space uses a fully

- **LGM** — image → 4 multiview images (ImageDream) → gaussians. `dylanebert/LGM-mini` is the clean diffusers-style duplicate target (both pipelines via `from_pretrained(..., trust_remote_code=True)`, output straight into `gr.Model3D`); `as

- **SHARP** — pip-installable (`sharp @ git+https://github.com/apple/ml-sharp.git@<sha>`), predicts a camera-space *scene* splat from one photo. Research-only license (`apple-amlr`) — tell the user before they build anything commercial. `pr

> **Verify against the live official Space before writing files.** Every pin below (torch/CUDA/Python versions, wheel URLs) reflects what the official Space shipped as of 2026-07 and tracks the ZeroGPU runtime, which changes. Fetch the curr

--extra-index-url https://download.pytorch.org/whl/cu130

kornia==0.8.2 timm==1.0.22 git+https://github.com/EasternJournalist/utils3d.git@9a4eb15e4021b67b12c460c7057d642626897ec8

timm==1.0.22 git+https://github.com/EasternJournalist/utils3d.git@9a4eb15e4021b67b12c460c7057d642626897ec8 https://github.com/adithyaxx/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu13torch2.11cxx11abiTRUE-cp312-cp312-linux_x8

git+https://github.com/EasternJournalist/utils3d.git@9a4eb15e4021b67b12c460c7057d642626897ec8 https://github.com/adithyaxx/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu13torch2.11cxx11abiTRUE-cp312-cp312-linux_x86_64.whl http

https://github.com/adithyaxx/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu13torch2.11cxx11abiTRUE-cp312-cp312-linux_x86_64.whl

https://github.com/LDYang694/Storages/releases/download/rtxpro6000/flex_gemm-1.0.0%2Btorch2.11.0.cu130-cp312-cp312-linux_x86_64.whl

https://github.com/LDYang694/Storages/releases/download/rtxpro6000/nvdiffrast-0.4.0%2Btorch2.11.0.cu130-cp312-cp312-linux_x86_64.whl

https://github.com/LDYang694/Storages/releases/download/rtxpro6000/nvdiffrec_render-0.0.0%2Btorch2.11.0.cu130-cp312-cp312-linux_x86_64.whl

https://github.com/LDYang694/Storages/releases/download/rtxpro6000/cumesh-0.0.1%2Btorch2.11.0.cu130-cp312-cp312-linux_x86_64.whl

https://github.com/LDYang694/Storages/releases/download/rtxpro6000/o_voxel-0.0.1%2Btorch2.11.0.cu130-cp312-cp312-linux_x86_64.whl

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

> **Verify against the live official Space before writing files.** Pins below are as of 2026-07. Fetch current files via `https://huggingface.co/spaces/<id>/raw/main/<path>` first.

subprocess.run(     shlex.split("pip install --no-build-isolation git+https://github.com/tatsy/torchmcubes.git"),

shlex.split("pip install --no-build-isolation git+https://github.com/tatsy/torchmcubes.git"),

[Credential-related source omitted]

**Requirements notes (2.1)** — fully pinned; the non-obvious entries: `--extra-index-url https://download.blender.org/pypi/` + `bpy==4.0` (Blender-as-pip; installs headless with no display setup — see [`3d-outputs.md`](3d-outputs.md) → Head

Blender shows up in 3D Spaces two ways: as the **`bpy` pip module** (`--extra-index-url https://download.blender.org/pypi/` + `bpy==<pin>`; Hunyuan3D-2.1 pins `bpy==4.0` — which installs cleanly on ZeroGPU with no display setup, though that

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Buckets are paid (per-TB storage). Check `whoami.canPay` and confirm with the user before creating one. Pricing + free tier: https://huggingface.co/storage.

Full docs: https://huggingface.co/docs/hub/storage-buckets.

To make the bucket files publicly addressable: leave the bucket public. Public bucket files are served at `https://huggingface.co/buckets/<ns>/<bucket>/resolve/<path>` (HTTP 302 redirect to a signed CDN URL). The Space writes once and the p

BUCKET_ID = "<ns>/<bucket-name>" BUCKET_URL = f"https://huggingface.co/buckets/{BUCKET_ID}/resolve"

BUCKET_URL = f"https://huggingface.co/buckets/{BUCKET_ID}/resolve"

Reference Space using this pattern: https://huggingface.co/spaces/victor/ace-step-jam

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

- **Hot-reload poisons factory reboot.** A commit that's only a hot-reload leaves runtime metadata that's valid only while the hot process is alive. `--factory-reboot` on top of one can fail with `fatal: could not read Username for 'https:/

[Credential-related source omitted]

import httpx r = httpx.post(f"https://<subdomain>.hf.space/your_route",

r = httpx.post(f"https://<subdomain>.hf.space/your_route",

[Credential-related source omitted]

2. **An SSH key registered on the user's HF profile.** Without this, SSH refuses the connection. If the user doesn't have one yet, they need to:    - Generate a keypair locally: `ssh-keygen -t ed25519 -f ~/.ssh/hf_dev -N ''` (no passphrase 

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

-H "Content-Type: application/json" \   "https://huggingface.co/api/spaces/<ns>/<space>/dev-mode" \   -d '{"enabled": true}'

"https://huggingface.co/api/spaces/<ns>/<space>/dev-mode" \

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

-H "Content-Type: application/json" \   "https://huggingface.co/api/spaces/<ns>/<space>/dev-mode" \   -d '{"enabled": false}'

"https://huggingface.co/api/spaces/<ns>/<space>/dev-mode" \

Guide: https://www.gradio.app/guides/custom-HTML-components

Example with a 3D camera-angle picker that makes sense in context: https://huggingface.co/spaces/multimodalart/qwen-image-multiple-angles-3d-camera

Reference Space: https://huggingface.co/spaces/huggingface-projects/rf-detr-realtime-webcam

curl "https://huggingface.co/api/models/<ns>/<repo>?expand[]=inferenceProviderMapping"

[Credential-related source omitted]

[Credential-related source omitted]

import subprocess, sys subprocess.run([sys.executable, "-m", "pip", "install", "--no-deps",                 "git+https://github.com/facebookresearch/demucs"], check=True)

subprocess.run([sys.executable, "-m", "pip", "install", "--no-deps",                 "git+https://github.com/facebookresearch/demucs"], check=True) import spaces

"git+https://github.com/facebookresearch/demucs"], check=True)

[Credential-related source omitted]

[Credential-related source omitted]

**Cause**: `@spaces.GPU(duration=N)` is larger than the visitor's tier per-call cap. **Fix**: Lower `N`. Tier caps live in the [ZeroGPU docs](https://huggingface.co/docs/hub/spaces-zerogpu).

**Fix**: Lower `N`. Tier caps live in the [ZeroGPU docs](https://huggingface.co/docs/hub/spaces-zerogpu).

[Credential-related source omitted]

[Credential-related source omitted]

**Cause**: Streaming endpoint (function uses `yield`), or a custom `gr.Server` `@app.get/post` route that doesn't appear in `view_api()`. **Fix**: For streaming, use `client.submit(...).result()` (or iterate the job). For custom routes, use

**Fix**: For streaming, use `client.submit(...).result()` (or iterate the job). For custom routes, use `httpx.post(base_url + "/route", ...)` directly — bypass `gradio_client`.

import subprocess, sys subprocess.run([sys.executable, "-m", "pip", "install", "--no-deps",                 "git+https://github.com/facebookresearch/demucs"], check=True)

subprocess.run([sys.executable, "-m", "pip", "install", "--no-deps",                 "git+https://github.com/facebookresearch/demucs"], check=True) import spaces  # safe now — torch wasn't touched

"git+https://github.com/facebookresearch/demucs"], check=True)

curl -s https://pypi.org/pypi/<pkg>/<version>/json    | python3 -c "import json,sys,re; rd=json.load(sys.stdin)['info'].get('requires_dist') or [];

curl -s https://pypi.org/pypi/<pkg>/<version>/json \

When PyPI is silent, fall back to the project's README compatibility table (torchcodec's lives at https://github.com/pytorch/torchcodec).

> https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels

https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve/main/wheels/<cell>/<wheel>

numpy einops https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve/main/wheels/pt212-cu130-cp310/flash_attn-2.8.3-cp310-cp310-linux_x86_64.whl

einops https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve/main/wheels/pt212-cu130-cp310/flash_attn-2.8.3-cp310-cp310-linux_x86_64.whl https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve

https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve/main/wheels/pt212-cu130-cp310/flash_attn-2.8.3-cp310-cp310-linux_x86_64.whl

https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve/main/wheels/pt212-cu130-cp310/xformers-0.0.34+3da0fc92.d20260528-cp39-abi3-linux_x86_64.whl

1. **kernels-community** — https://huggingface.co/kernels-community handles ABI matching for you. Often the simplest path; no version pinning needed.

2. **Upstream wheel matrix** — e.g. flash-attention's releases page ships a fairly complete `cu12 / torch / Python` matrix at https://github.com/Dao-AILab/flash-attention/releases. Pin `torch==X.Y.Z` in `requirements.txt` to match the wheel

For numerical limits (per-tier daily quota minutes, runs-per-day caps, current backing GPU, supported Python / torch versions): https://huggingface.co/docs/hub/spaces-zerogpu. Those values change over time and are deliberately kept out of t

[Credential-related source omitted]

[Credential-related source omitted]

- `multimodalart/Boogu-Image-0.1-Edit-aoti-compile` (compile + upload) and `multimodalart/Boogu-Image` (serving via block loading) — the blocks pattern end to end. - `zerogpu-aoti/Qwen-Image`, `zerogpu-aoti/Wan2` — artifact repos showing th

- Deeper background on inductor configs and dynamic shapes: https://huggingface.co/blog/zerogpu-aoti

[Credential-related source omitted]

- https://huggingface.co/spaces/diffusers/unofficial-SDXL-Turbo-i2i-t2i

- https://huggingface.co/spaces/huggingface-projects/rf-detr-realtime-webcam

- Non-destructive scripts should be tested before handing over to the User  - Shell scripts are preferred, but use Python or TSX if complexity or user need requires it.  - IMPORTANT: Use the `HF_TOKEN` environment variable as an Authorizati

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

The following are the main API endpoints available at `https://huggingface.co`

The API is documented with the OpenAPI standard at `https://huggingface.co/.well-known/openapi.json`.

**IMPORTANT:** DO NOT ATTEMPT to read `https://huggingface.co/.well-known/openapi.json` directly as it is too large to process.

curl -s "https://huggingface.co/.well-known/openapi.json" | jq '.paths | keys | sort'

curl -s "https://huggingface.co/.well-known/openapi.json" | jq '.paths["/api/models"]'

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

url = f"https://huggingface.co/api/models?limit={limit}"

req = urllib.request.Request(url, headers=headers)

with urllib.request.urlopen(req) as resp:

#!/usr/bin/env bash

[Credential-related source omitted]

[Credential-related source omitted]

curl -s "${headers[@]}" "https://huggingface.co/api/models?limit=${LIMIT}"

#!/usr/bin/env tsx

[Credential-related source omitted]

const url = `https://huggingface.co/api/models?limit=${limit}`;

(async () => {   const res = await fetch(url, { headers });

const res = await fetch(url, { headers });

#!/bin/bash

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

API_URL="https://huggingface.co/api/models"

# Build curl command with authentication if available

CURL_CMD="curl -s $AUTH_HEADER \"$API_URL?search=$SEARCH_QUERY&limit=50\""

echo -e "${BLUE}API Query: $API_URL?search=$SEARCH_QUERY&limit=50${NC}"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

else     RESPONSE=$(curl -s "$API_URL?search=$SEARCH_QUERY&limit=50" || true) fi

RESPONSE=$(curl -s "$API_URL?search=$SEARCH_QUERY&limit=50" || true)

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

else             RESPONSE=$(curl -s "$API_URL?search=$SEARCH_QUERY&limit=50" || true)         fi

RESPONSE=$(curl -s "$API_URL?search=$SEARCH_QUERY&limit=50" || true)

#!/usr/bin/env bash

[Credential-related source omitted]

[Credential-related source omitted]

local url="https://huggingface.co/api/models/${model_id}"     local response     response=$(curl -s "${headers[@]}" "$url" 2>/dev/null || true)

response=$(curl -s "${headers[@]}" "$url" 2>/dev/null || true)

#!/usr/bin/env bash

[Credential-related source omitted]

[Credential-related source omitted]

rm -rf "$tmp_dir"

[Credential-related source omitted]

[Credential-related source omitted]

#!/usr/bin/env bash

[Credential-related source omitted]

[Credential-related source omitted]

curl -s "${headers[@]}" "$url" 2>/dev/null || echo '{"error": "Network error"}'

local api_url="https://huggingface.co/api/models/$model_id"

[Credential-related source omitted]

local card_url="https://huggingface.co/$model_id/raw/main/README.md"     local card_content=$(curl -s "$card_url" 2>/dev/null || echo "")

local card_content=$(curl -s "$card_url" 2>/dev/null || echo "")

local trending_url="https://huggingface.co/api/trending?type=model&limit=$limit"

text="Loss 5.2 still high after 200 steps", # Detailed description (optional)     level=trackio.AlertLevel.WARN,               # INFO, WARN, or ERROR (default: WARN)     webhook_url="https://hooks.slack.com/...",   # Per-alert webhook overr

level=trackio.AlertLevel.WARN,               # INFO, WARN, or ERROR (default: WARN)     webhook_url="https://hooks.slack.com/...",   # Per-alert webhook override (optional) )

webhook_url="https://hooks.slack.com/...",   # Per-alert webhook override (optional)

trackio.init(     project="my-project",     webhook_url="https://hooks.slack.com/services/...",

project="my-project",     webhook_url="https://hooks.slack.com/services/...",     webhook_min_level=trackio.AlertLevel.WARN,  # Only send WARN+ to webhook

webhook_url="https://hooks.slack.com/services/...",

title="Critical failure",     level=trackio.AlertLevel.ERROR,     webhook_url="https://hooks.slack.com/services/...",  # Overrides global URL

level=trackio.AlertLevel.ERROR,     webhook_url="https://hooks.slack.com/services/...",  # Overrides global URL )

webhook_url="https://hooks.slack.com/services/...",  # Overrides global URL

- **GitHub**: [gradio-app/trackio](https://github.com/gradio-app/trackio)

- **Docs**: [huggingface.co/docs/trackio](https://huggingface.co/docs/trackio/index)

<iframe    src="https://username-trackio.hf.space/?project=my-project&metrics=train_loss,val_loss&sidebar=hidden"

src="https://username-trackio.hf.space/?project=my-project&metrics=train_loss,val_loss&sidebar=hidden"

### Account & Authentication - Hugging Face Account with [Pro](https://hf.co/pro), [Team](https://hf.co/enterprise), or [Enterprise](https://hf.co/enterprise) plan (Jobs require paid plan)

- Hugging Face Account with [Pro](https://hf.co/pro), [Team](https://hf.co/enterprise), or [Enterprise](https://hf.co/enterprise) plan (Jobs require paid plan)

1. **Save the script locally** to `submitted_jobs/` in the workspace root (create if needed) with a descriptive name like `training_<dataset>_<YYYYMMDD_HHMMSS>.py`. Tell the user the path. 2. **Submit** using `hf_jobs` MCP tool (preferred)