funsloth-upload
Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation
What this skill does
# Model Upload & Card Generator
Create model cards and upload fine-tuned models to Hugging Face Hub.
## Gather Context
If coming from training manager, you should have:
- `model_path`, `base_model`, `dataset`, `technique`
- `training_config` (LoRA rank, LR, epochs)
- `final_loss`, `training_time`, `hardware`
If missing, ask for essential information.
## Configuration
### 1. Repository Settings
Ask for:
- **Repo name**: `username/model-name`
- **Visibility**: Public or Private
- **License**: MIT, Apache 2.0, CC-BY-4.0, Llama 3 Community, etc.
### 2. Export Formats
Options:
1. **LoRA adapter only** (~50-200MB) - Users merge themselves
2. **Merged 16-bit** (15-140GB) - Ready to use
3. **GGUF quantized** (4-8GB) - For llama.cpp/Ollama
4. **All of the above** (Recommended)
### 3. GGUF Quantization
If GGUF selected, ask which levels. See [references/GGUF_GUIDE.md](references/GGUF_GUIDE.md).
| Method | Size | Quality |
|--------|------|---------|
| Q4_K_M | ~4GB | Good (Recommended) |
| Q5_K_M | ~5GB | Better |
| Q8_0 | ~8GB | Best |
## Generate Model Card
Create README.md with:
1. **YAML Metadata** - license, tags, base_model, datasets
2. **Model Description** - Table with key attributes
3. **Training Details** - Hyperparameters, LoRA config, results
4. **Usage Examples** - Transformers, Unsloth, Ollama, llama.cpp
5. **Intended Use** - Primary use cases, out-of-scope
6. **Limitations** - Biases, known issues
7. **Citation** - BibTeX entry
## Execute Upload
### 1. Create Repository
```python
from huggingface_hub import create_repo
create_repo("username/model-name", private=False, exist_ok=True)
```
### 2. Upload Files
```python
from huggingface_hub import HfApi
api = HfApi()
# LoRA adapter
api.upload_folder(folder_path="./outputs/lora_adapter", repo_id="username/model")
# Model card
api.upload_file(path_or_fileobj="README.md", path_in_repo="README.md", repo_id="username/model")
```
### 3. Generate GGUF (if selected)
```python
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained("./outputs/lora_adapter")
model.save_pretrained_gguf("./gguf", tokenizer, quantization_method="q4_k_m")
```
Use [scripts/convert_gguf.py](scripts/convert_gguf.py) for multiple quantizations.
### 4. Verify
```python
from huggingface_hub import list_repo_files
print(list_repo_files("username/model"))
```
## Final Report
> **Upload Complete!**
>
> Model: https://huggingface.co/{repo_name}
>
> **Uploaded:**
> - LoRA adapter
> - Model card
> - GGUF files (if selected)
>
> **Next steps:**
> - Verify model page
> - Add example outputs
> - Run benchmarks
> - Share on social media
## Model Card Best Practices
1. **Be specific about limitations**
2. **Include usage examples** - copy-pasteable
3. **Document training details**
4. **Credit sources** - base model, dataset, tools
5. **Use tables** - easier to scan
## Error Handling
| Error | Resolution |
|-------|------------|
| Repo exists | Use `exist_ok=True` |
| Permission denied | Check HF token has write access |
| Upload timeout | Use chunked upload |
## Bundled Resources
- [scripts/convert_gguf.py](scripts/convert_gguf.py) - GGUF conversion
- [references/GGUF_GUIDE.md](references/GGUF_GUIDE.md) - GGUF details and Ollama setup
- [references/TROUBLESHOOTING.md](references/TROUBLESHOOTING.md) - Upload issues
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.