Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
OpenAI: gpt-oss-120b (batch)
Modelsgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
openai/gpt-oss-120b:batch -
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
qwen/qwen3-235b-a22b-2507 -
Mistral: Mistral Medium 3
ModelsMistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
mistralai/mistral-medium-3 -
OpenAI: GPT-4.1 (batch)
ModelsGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
openai/gpt-4.1:batch -
Qwen: Qwen3.8 27B (batch)
ModelsQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
qwen/qwen3.8-27b:batch -
FLAN
Datasets & benchmarksHugging Face dataset by Open-Orca
Open-Orca/FLAN -
Docmatix
Datasets & benchmarksHugging Face dataset by HuggingFaceM4
HuggingFaceM4/Docmatix -
Benzi
Tools & appsBenzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, control flow and class hierarchy first; then it reads, explains, runs, edits and verifies your code using it. Every language runs its own tree-sitter grammar into the same query map.
git clone https://github.com/oooscoos/Benzi.git -
harmful_behaviors
Datasets & benchmarksHugging Face dataset by mlabonne
mlabonne/harmful_behaviors -
ai-village
Datasets & benchmarksHugging Face dataset by aidigestorg
aidigestorg/ai-village -
coyo-700m
Datasets & benchmarksHugging Face dataset by kakaobrain
kakaobrain/coyo-700m -
xlam-function-calling-60k
Datasets & benchmarksHugging Face dataset by Salesforce
Salesforce/xlam-function-calling-60k -
EgoStandard
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoStandard -
agent-lsp
MCP serversLanguage servers as 66 code-intelligence tools for AI agents, CI-verified on 32 languages.
@blackwell-systems/agent-lsp@0.24.2 -
textbook_quality_programming
Datasets & benchmarksHugging Face dataset by vikp
vikp/textbook_quality_programming -
KoCommercial-Dataset
Datasets & benchmarksHugging Face dataset by MarkrAI
MarkrAI/KoCommercial-Dataset -
ABC-130k
Datasets & benchmarksHugging Face dataset by XDOF
XDOF/ABC-130k -
ChatQA-Training-Data
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/ChatQA-Training-Data -
hermes_reasoning_tool_use
Datasets & benchmarksHugging Face dataset by interstellarninja
interstellarninja/hermes_reasoning_tool_use -
DeepScaleR-Preview-Dataset
Datasets & benchmarksHugging Face dataset by agentica-org
agentica-org/DeepScaleR-Preview-Dataset -
reasoning-v1-20m
Datasets & benchmarksHugging Face dataset by glaiveai
glaiveai/reasoning-v1-20m -
Nemotron-Personas-Korea
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Nemotron-Personas-Korea -
Qwen: Qwen3 VL 8B Instruct
ModelsQwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...
qwen/qwen3-vl-8b-instruct -
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
qwen/qwen3-235b-a22b-thinking-2507
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.