🔄 In a Training Loop

Charles

qikp

·

https://qikp.statichost.page/

AI & ML interests

Training small causal language models and classifiers, and data manipulation. he/they

Recent Activity

liked a Space 3 days ago

not-lain/background-removal

updated a model 10 days ago

qikp/humanizer-135m-sft-GGUF

published a model 10 days ago

qikp/humanizer-135m-sft-GGUF

View all activity

Organizations

New activity in burner22/numbat 11 days ago

Ran the full checkpoint: perplexity 7e9, random layers, embeddings borrowed from a real model

#50 opened 12 days ago by

New activity in SupraLabs/Supra2.6-Pico 11 days ago

Explanation of the benchmark contamination

#1 opened 11 days ago by

New activity in AxiomicLabs/Open_SLM_Leaderboard 11 days ago

Broken

#299 opened 11 days ago by

New activity in AxiomicLabs/Open_SLM_Leaderboard 14 days ago

Add Supra2.6-Pico (SupraLabs, 2.97M)

#284 opened 15 days ago by

New activity in reflection/Beam-1.0-501B-A23B 20 days ago

Reward-hacking garbage

#18 opened 23 days ago by

New activity in SupraLabs/Supra2.1-Ultra about 1 month ago

Why Llama?

#1 opened about 1 month ago by

New activity in AxiomicLabs/Open_SLM_Leaderboard about 1 month ago

🚩 Missing models

#224 opened about 1 month ago by

New activity in LiquidAI/LFM2.5-24B-A2B about 1 month ago

LFM2.5 700M with Thinking?

#5 opened about 1 month ago by

New activity in appvoid/void.0 about 1 month ago

llama.cpp tokenizer fix

#2 opened about 1 month ago by

New activity in AxiomicLabs/GPT-X3-150M about 1 month ago

ClimbMix usage

#6 opened about 1 month ago by

Can we get a GGUF?

#7 opened about 1 month ago by

New activity in Cactus-Compute/whistle about 1 month ago

Parameter count

#2 opened about 1 month ago by

New activity in Compactbot/checkpoint-health about 1 month ago

Neat!

#1 opened about 1 month ago by

New activity in AxiomicLabs/FactBase-DCLM about 1 month ago

Use cases?

#1 opened about 1 month ago by

New activity in qikp/qes about 1 month ago

Experiments

#1 opened about 1 month ago by

New activity in Compactbot/edu-classifier-stress-test about 1 month ago

Expanded version

#1 opened about 1 month ago by

New activity in Compactbot/about-me about 1 month ago

Can you follow me?

#3 opened about 1 month ago by

New activity in qikp/kite-8.1-11m-base about 1 month ago

Call for testing

#1 opened about 1 month ago by

New activity in SupraLabs/Supra-Reasoning-CoT-Dataset-v2 about 1 month ago

Terrible advice

#1 opened about 1 month ago by

New activity in PleIAs/baguettotron-600m about 1 month ago

Chat template reasoning content not handled properly

#1 opened about 1 month ago by