Naphula's picture

In a Training Loop 🔄

Naphula

Naphula

·

AI & ML interests

Building new model tools, merges (7B-70B), merge methods, ablations, finetunes, and datasets.

Recent Activity

updated a collection about 10 hours ago

Favorite Models

upvoted a paper about 11 hours ago

The Unreasonable Ineffectiveness of the Deeper Layers

upvoted a paper about 11 hours ago

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit

View all activity

Organizations

New activity in QuantFactory/Loki-v2.6-8b-1024k-GGUF about 13 hours ago

insane yaml

#1 opened about 13 hours ago by

New activity in mradermacher/model_requests about 16 hours ago

https://huggingface.co/Naphula/Salamander-24B-v1

#2307 opened about 16 hours ago by

New activity in Naphula/model_tools 3 days ago

graph_v18 variants for runpod

#7 opened 3 days ago by

config.py patch

#6 opened 3 days ago by

New activity in Naphula/Slimaki-24B-v1.2 6 days ago

Partly broken

#1 opened 6 days ago by

New activity in DarkArtsForge/Magistaroth-24B-v1.2 6 days ago

Interesting model

#1 opened 6 days ago by

New activity in Naphula-Archives/Fat_Fish-MPOA 10 days ago

model.safetensors.index.json for original fat_fish

#1 opened 10 days ago by

New activity in DarkArtsForge/Magistaroth-24B-v1.1 10 days ago

Question

#3 opened 2 months ago by

New activity in mradermacher/model_requests 10 days ago

Ancient Awakening MPOA

#2223 opened 13 days ago by

New activity in DarkArtsForge/Magistaroth-24B-v1.1 10 days ago

Comparison

#5 opened 12 days ago by

New activity in Naphula/Goetia-8B-v1 11 days ago

Endless loop

#1 opened 11 days ago by

New activity in mradermacher/model_requests 11 days ago

Ancient Awakening MPOA

#2223 opened 13 days ago by

New activity in DarkArtsForge/Magistaroth-24B-v1.1 11 days ago

Comparison

#5 opened 12 days ago by