Skip to content

Marketplace

Everything your AI needs, in one place.

Ready-made agents, skills, personas, prompts, templates and tools. Each one is checked before it goes live, works with any model, and installs in a click. Rate what you use so the best rises to the top.

143.8K
listings
1
installs
0
reviews
38.7K
publishers
24 results
Skill

knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source

by davila7skills.sh
(0)
0Free
Skill

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond

by davila7skills.sh
(0)
0Free
Skill

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving

by davila7skills.sh
(0)
0Free
Skill

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabli

by davila7skills.sh
(0)
0Free
Skill

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l

by davila7skills.sh
(0)
0Free
Skill

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap

by davila7skills.sh
(0)
0Free
Skill

knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source

by orchestra-researchskills.sh
(0)
0Free
Skill

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond

by orchestra-researchskills.sh
(0)
0Free
Skill

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving

by orchestra-researchskills.sh
(0)
0Free
Skill

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabli

by orchestra-researchskills.sh
(0)
0Free
Skill

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l

by orchestra-researchskills.sh
(0)
0Free
Skill

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap

by orchestra-researchskills.sh
(0)
0Free
Skill

knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source

by ovachieverskills.sh
(0)
0Free
Skill

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond

by ovachieverskills.sh
(0)
0Free
Skill

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving

by ovachieverskills.sh
(0)
0Free
Skill

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabli

by ovachieverskills.sh
(0)
0Free
Skill

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l

by ovachieverskills.sh
(0)
0Free
Skill

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap

by ovachieverskills.sh
(0)
0Free
Skill

knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source

by majiayu000GitHub
(0)
0Free
Skill

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap

by chen-yu-haoGitHub
(0)
0Free
Skill

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap

by majiayu000GitHub
(0)
0Free
Skill

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l

by ihatesea69GitHub
(0)
0Free
Skill

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures l

by nota-americaGitHub
(0)
0Free
Skill

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond

by wang030327-botGitHub
(0)
0Free
1

Find

Search or browse by kind. Every card shows who made it, how many people installed it and what they think.

2

Install

One click. You get a manifest the router understands, plus copy-paste snippets for the CLI, Python and YAML.

3

Rate and publish

Leave a star rating after you have used it. Made something useful? Publish it - free listings go live immediately.

Prefer the terminal? osr stack apply registry://starter installs the starter template.