bitsandbytes Model Quantization
Orchestra-Research/AI-Research-SKILLs
Loads large language models in 8-bit or 4-bit with bitsandbytes so they fit smaller GPUs, and sets up QLoRA fine-tuning on a 4-bit base model.
Guides building on the 0G Compute Network, a decentralized GPU marketplace for AI inference and fine-tuning, with SDK patterns and CLI commands.
Install 0G Compute Network Guide
$ npx skills add internet-court/internet-court-skill --skill 0g-compute -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install internet-court/internet-court-skill 0g-compute --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vendored/0g/0g-compute .claude/skills/0g-compute && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "0g-compute" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-compute into .claude/skills/0g-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "0g-compute", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-computeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add internet-court/internet-court-skill --skill 0g-compute -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install internet-court/internet-court-skill 0g-compute --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/vendored/0g/0g-compute .agents/skills/0g-compute && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "0g-compute" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-compute into .agents/skills/0g-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "0g-compute", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add internet-court/internet-court-skill --skill 0g-compute -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install internet-court/internet-court-skill 0g-compute --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/vendored/0g/0g-compute .cursor/skills/0g-compute && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "0g-compute" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-compute into .cursor/skills/0g-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "0g-compute", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/internet-court/internet-court-skill.git --path vendored/0g/0g-compute--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add internet-court/internet-court-skill --skill 0g-compute -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install internet-court/internet-court-skill 0g-compute --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/vendored/0g/0g-compute .gemini/skills/0g-compute && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "0g-compute" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-compute into .gemini/skills/0g-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "0g-compute", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install internet-court/internet-court-skill 0g-computeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add internet-court/internet-court-skill --skill 0g-compute -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/vendored/0g/0g-compute .github/skills/0g-compute && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "0g-compute" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-compute into .github/skills/0g-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "0g-compute", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add internet-court/internet-court-skill --skill 0g-compute -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install internet-court/internet-court-skill 0g-compute --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/vendored/0g/0g-compute .opencode/skills/0g-compute && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "0g-compute" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/0g/0g-compute into .opencode/skills/0g-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "0g-compute", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
0g-compute- GitHub stars
- 6.6k
- Used in
- 1 other repo
- Token cost
- ~1.9k tokens
- SKILL.md length
- 355 words
- Files
- 11 (incl. references)
- Skills in repo
- 80
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Guides building on the 0G Compute Network, a decentralized GPU marketplace for AI inference and fine-tuning, with SDK patterns and CLI commands.
- Works in 4 steps: Copy code patterns from this skill… → Call processResponse() after every API… → Use environment variables for private… → …
- Building an app that runs inference on the 0G Compute Network
- SKILL.md covers Code Generation Rules, Network Information, Prerequisites and Quick Setup, plus 7 more sections
- Calls pnpm and node; reaches evmrpc.0g.ai and evmrpc-testnet.0g.ai; needs PRIVATE_KEY
What it does
The skill covers building with the 0G Compute Network for chatbots, image generation, speech-to-text and fine-tuning, using the @0glabs/0g-serving-broker SDK and the 0g-compute-cli command-line tool. Its code generation rules say to copy patterns verbatim rather than rely on training data, to call processResponse after every API response for fee settlement and TEE verification, to keep private keys in environment variables and to start on testnet.
It lists mainnet and testnet RPC endpoints, both supporting inference and fine-tuning, says to check current models with listService or the CLI's provider listing because availability changes, and requires Node.js 22.0.0 or newer. Quick setup runs setup-network, logs in with a wallet key and deposits funds. Reference files cover inference, fine-tuning, account management and production examples such as streaming chat, text-to-image and speech-to-text.
When your agent uses it
- Building an app that runs inference on the 0G Compute Network
- Fine-tuning a model on decentralized GPUs
- Managing a 0G compute account and deposits
- Listing available providers and models
Example prompts
- “Write a streaming chat client for the 0G Compute Network using the serving broker SDK.”
- “How do I fine-tune a model on 0G compute? Start on testnet.”
- “List the inference providers available through the 0g-compute-cli.”
- “Add processResponse handling to my 0G text-to-image script.”
Requirements
- Node.js 22.0.0 or newer
- The @0glabs/0g-serving-broker package
- A wallet private key kept in an environment variable
- Funds deposited in a 0G compute account
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Copy code patterns from this skill verbatim. Do NOT generate from training data.
- Call processResponse() after every API response (see processResponse section below).
- Use environment variables for private keys. Never hardcode secrets.
- Route users to testnet for initial development.
What it can do on your machine
Read from SKILL.md and the folder at commit fa89195. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pnpmnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
evmrpc.0g.aievmrpc-testnet.0g.ai
Also links to:
github.comdiscord.gg
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
PRIVATE_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
0G Compute Network Guide loads about 1.9k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 355 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 355 words (~1,861 tokens).
“This skill provides instructions for building with the 0G Compute Network — a decentralized GPU marketplace for AI inference and model fine-tuning. Follow these patterns exactly when generating code.”
- name
- 0g-compute
Files
SKILL.md and 10 other files (references) in vendored/0g/0g-compute of internet-court/internet-court-skill.
- SKILL.md
- .github/workflows/claude-code-review.yml
- LICENSE
- README.md
- references/account-management.md
- references/examples/README.md
- references/examples/speech-to-text.md
- references/examples/streaming-chat.md
- references/examples/text-to-image.md
- references/fine-tuning.md
- references/inference.md
Open the folder on GitHubat commit fa89195
Used in 1 other repository
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in internet-court/internet-court-skill, which our catalogue first saw on October 7, 2026.
Compare with similar skills
0G Compute Network Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| 0G Compute Network Guide this skillinternet-court/internet-court-skill | 6.6k | 1 repos | ~1.9k | Automated safety check: Pass | Custom licence | |
| bitsandbytes Model QuantizationOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Hugging Face Local Model Evalshuggingface/skills | 11k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Hugging Face LLM Trainerhuggingface/skills | 11k | 1 repos | ~7.2k | Automated safety check: Pass | Apache-2.0 | |
| Ascend Model Adapter for vLLMvllm-project/vllm-ascend | 2.9k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
- Official
Hugging Face LLM Trainer
huggingface/skills
Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.
Ascend Model Adapter for vLLM
vllm-project/vllm-ascend
Adapts and debugs Hugging Face or local models to run on vLLM with Ascend NPU, validates them by serving, and delivers the result as one signed commit.
Graphsignal
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
- Official
Hugging Face Vision Trainer
huggingface/skills
Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.
More from internet-court/internet-court-skill
All 80 skills in this repoKleros IPFS Upload
internet-court/internet-court-skill
Uploads one Kleros-related file per paid request to IPFS through the Kleros x402 gateway for 0.01 USDC on Base, returning a CID that Kleros contracts can reference.
PNP Prediction Markets on Solana
internet-court/internet-court-skill
Creates, trades and settles permissionless prediction markets on Solana with any SPL token as collateral, including social-media and custom-oracle markets.
BNB Chain MCP Server
internet-court/internet-court-skill
Connects an agent to the BNB Chain MCP server to read blocks and contracts, move tokens and NFTs, register ERC-8004 agents and use Greenfield storage.
GenLayer ERC-7710 Connector
internet-court/internet-court-skill
Specifies how a GenLayer Intelligent Contract decision about an agent's performance becomes an ERC-7710 revocation or policy change, through a relayer or bridge and an EVM controller.
GenLayer Agent Supervision Adapter
internet-court/internet-court-skill
Specifies how a GenLayer Intelligent Contract should supervise an AI agent, with review rubrics, evidence schemas and continue, warn, constrain or revoke decisions.
Heurist Mesh Crypto Data
internet-court/internet-court-skill
Pulls live crypto token data, DeFi metrics, wallet holdings, project research and Twitter/X signals through Heurist Mesh agents over a REST API.
Related
Works with
Categories
Questions about 0G Compute Network Guide
What does 0G Compute Network Guide do?
Guides building on the 0G Compute Network, a decentralized GPU marketplace for AI inference and fine-tuning, with SDK patterns and CLI commands. The skill covers building with the 0G Compute Network for chatbots, image generation, speech-to-text and fine-tuning, using the @0glabs/0g-serving-broker SDK and the 0g-compute-cli command-line tool. Its code generation rules say to copy patterns verbatim rather than rely on training data, to call processResponse after every API response for fee settlement and TEE verification, to keep private keys in environment variables and to start on testnet.
When should I use 0G Compute Network Guide?
0G Compute Network Guide fits situations like: building an app that runs inference on the 0G Compute Network; fine-tuning a model on decentralized GPUs; managing a 0G compute account and deposits; listing available providers and models.
How do I install 0G Compute Network Guide in Claude Code?
Run `npx skills add internet-court/internet-court-skill --skill 0g-compute -a claude-code`. Or copy the skill folder (vendored/0g/0g-compute in internet-court/internet-court-skill) into .claude/skills/0g-compute in your project. Claude Code loads it when a task matches its description.
How do I install 0G Compute Network Guide in Codex?
Run `npx skills add internet-court/internet-court-skill --skill 0g-compute -a codex`. Or copy the skill folder (vendored/0g/0g-compute in internet-court/internet-court-skill) into .agents/skills/0g-compute in your project. Codex loads it when a task matches its description.
Can I use 0G Compute Network Guide in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add internet-court/internet-court-skill --skill 0g-compute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/0g-compute, .gemini/skills/0g-compute, .github/skills/0g-compute and .opencode/skills/0g-compute in your project.
What does 0G Compute Network Guide need to run?
Going by SKILL.md and its folder, 0G Compute Network Guide needs the command-line tools its instructions call (pnpm and node) and credentials named PRIVATE_KEY. Our summary lists: Node.js 22.0.0 or newer; The @0glabs/0g-serving-broker package; A wallet private key kept in an environment variable; Funds deposited in a 0G compute account.
Does 0G Compute Network Guide access the network?
SKILL.md names 4 domains. In commands or code: evmrpc.0g.ai and evmrpc-testnet.0g.ai; the agent is likely to contact these when it follows the instructions. As links in the text: github.com and discord.gg. This is read from the text; nothing was executed.
Is 0G Compute Network Guide safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does 0G Compute Network Guide use?
0G Compute Network Guide has a licence file (from the LICENSE file in the skill folder) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does 0G Compute Network Guide use?
About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 27k tokens, read only when the agent opens those files.
What are the alternatives to 0G Compute Network Guide?
Skills that share tags, products or a category with 0G Compute Network Guide: bitsandbytes Model Quantization (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), Hugging Face LLM Trainer (huggingface/skills, 11k stars) and Ascend Model Adapter for vLLM (vllm-project/vllm-ascend, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains 0G Compute Network Guide?
internet-court (a GitHub organization) maintains it in internet-court/internet-court-skill, which has 6,551 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on August 19, 2026.
Source: internet-court/internet-court-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.