minpeter's picture

minpeter

minpeter

·

https://minpeter.xyz

minpeter

AI & ML interests

None yet

Recent Activity

liked a model about 14 hours ago

NovaSky-AI/Sky-T1-32B-Flash

replied to sometimesanotion's post 1 day ago

I've managed a #1 score of 41.22% average for 14B parameter models on the Open LLM Leaderboard. As of this writing, sometimesanotion/Lamarck-14B-v0.7 is #8 for all models up to 70B parameters. It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.

reacted to sometimesanotion's post with 🔥 1 day ago

I've managed a #1 score of 41.22% average for 14B parameter models on the Open LLM Leaderboard. As of this writing, sometimesanotion/Lamarck-14B-v0.7 is #8 for all models up to 70B parameters. It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.

View all activity

Organizations

minpeter's activity

upvoted an article 3 days ago

Article

Hugging Face and FriendliAI partner to supercharge model deployment on the Hub

4 days ago

• 29

upvoted a collection 4 days ago

Adventure LoRAs

LoRAs trained on text adventure data, quality variable • 9 items • Updated Nov 7, 2024 • 2

upvoted a collection 8 days ago

Extracted LoRA (mergekit)

PEFT-compatible LoRA adapters produced by mergekit-extract-lora • 17 items • Updated 2 days ago • 3

upvoted a collection 17 days ago

Phi-4

Phi-4 small language model. • 2 items • Updated 17 days ago • 43

upvoted 2 collections 19 days ago

Cosmos

The collection of Cosmos models • 31 items • Updated 9 days ago • 249

Dolphin 3.0

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 7 items • Updated 20 days ago • 57

upvoted a collection 23 days ago

Hammer2.1

Hammer: a series of lightweight language models with strong function calling capability • 4 items • Updated Dec 13, 2024 • 1

upvoted a collection about 2 months ago

Oxy 1

Our first fine tunes, very experimental... • 5 items • Updated 27 days ago • 2

upvoted 3 collections 2 months ago

NexusRaven V2 Function Calling Benchmark

10 items • Updated Dec 14, 2023 • 5

Athene-V2

2 items • Updated Nov 14, 2024 • 7

Hermes 3

The Hermes 3 Series of Models • 10 items • Updated Dec 11, 2024 • 101

upvoted 2 collections 3 months ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated Dec 18, 2024 • 96

Open LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 63 items • Updated about 1 hour ago • 513