ggml.ai

company

https://ggml.ai

ggerganov

ggml-org

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

ngxson authored a paper about 1 hour ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

reach-vb authored a paper about 1 hour ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

danbev updated a model about 5 hours ago

ggml-org/bge-small-en-v1.5-Q8_0-GGUF

View all activity

Articles

Introduction to ggml

Aug 13, 2024

• 140

ggml-org's activity

ngxson

authored a paper about 1 hour ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 1 day ago • 58

reach-vb

authored a paper about 1 hour ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 1 day ago • 58

danbev

updated a model about 5 hours ago

ggml-org/bge-small-en-v1.5-Q8_0-GGUF

Feature Extraction • Updated about 5 hours ago

danbev

updated a collection about 5 hours ago

llama.cpp presets

Collection

Models that are used for presets in llama.cpp. • 3 items • Updated about 5 hours ago

danbev

updated a model about 5 hours ago

ggml-org/e5-small-v2-Q8_0-GGUF

danbev

updated a collection about 6 hours ago

llama.cpp presets

Collection

Models that are used for presets in llama.cpp. • 3 items • Updated about 5 hours ago

danbev

updated a model about 6 hours ago

ggml-org/gte-small-Q8_0-GGUF

danbev

updated a collection about 6 hours ago

llama.cpp presets

Collection

Models that are used for presets in llama.cpp. • 3 items • Updated about 5 hours ago

ggerganov

updated a collection 6 days ago

llama.vim

Collection

ggerganov

updated a model 6 days ago

ggml-org/Qwen2.5-Coder-0.5B-Q8_0-GGUF

Text Generation • Updated 6 days ago • 160

ngxson

updated a collection 14 days ago

GGUF LoRA adapters

Collection

Adapters extracted from fine tuned models, using mergekit-extract-lora • 16 items • Updated 14 days ago • 4

ngxson

updated a collection 15 days ago

GGUF LoRA adapters

Collection

Adapters extracted from fine tuned models, using mergekit-extract-lora • 16 items • Updated 14 days ago • 4

ngxson

posted an update 16 days ago

Post

691

Fun fact: you can get any DeepSeek-R1-Qwen **abliterated** by using one of these LoRA adapters (GGUF available!)

ngxson/extracted-lora-mergekit-677d5c3eea0b6a7661201846

ggerganov

updated 2 models 17 days ago

ggml-org/DeepSeek-R1-Distill-Qwen-32B-Q8_0-GGUF

Updated 17 days ago • 7.43k • 5

ggml-org/DeepSeek-R1-Distill-Qwen-1.5B-Q4_0-GGUF

Updated 17 days ago • 3.54k • 2

ngxson

updated a collection 22 days ago

GGUF LoRA adapters

Collection

Adapters extracted from fine tuned models, using mergekit-extract-lora • 16 items • Updated 14 days ago • 4

ngxson

posted an update 23 days ago

Post

2675

Check out my collection of pre-made GGUF LoRA adapters!

This allow you to use both normal + abliterated version of popular models like llama, qwen, etc, without having to double to amount of VRAM usage.

ngxson/gguf_lora_collection