🔄 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

published a model about 23 hours ago

qikp/kite-9-16m-base

updated a model 5 days ago

qikp/kite-9-16m-base

new activity 5 days ago

reflection/Beam-1.0-501B-A23B:Reward-hacking garbage

View all activity

Organizations

New activity in reflection/Beam-1.0-501B-A23B 5 days ago

Reward-hacking garbage

#18 opened 8 days ago by

New activity in SupraLabs/Supra2.1-Ultra 18 days ago

Why Llama?

#1 opened 18 days ago by

New activity in AxiomicLabs/Open_SLM_Leaderboard 18 days ago

🚩 Missing models

#224 opened 18 days ago by

New activity in LiquidAI/LFM2.5-24B-A2B 18 days ago

LFM2.5 700M with Thinking?

#5 opened 18 days ago by

New activity in appvoid/void.0 19 days ago

llama.cpp tokenizer fix

#2 opened 19 days ago by

New activity in AxiomicLabs/GPT-X3-150M 19 days ago

ClimbMix usage

#6 opened 20 days ago by

Can we get a GGUF?

#7 opened 19 days ago by

New activity in Cactus-Compute/whistle 20 days ago

Parameter count

#2 opened 20 days ago by

New activity in Compactbot/checkpoint-health 21 days ago

Neat!

#1 opened 21 days ago by

New activity in AxiomicLabs/FactBase-DCLM 21 days ago

Use cases?

#1 opened 21 days ago by

New activity in qikp/qes 21 days ago

Experiments

#1 opened 23 days ago by

New activity in Compactbot/edu-classifier-stress-test 22 days ago

Expanded version

#1 opened 22 days ago by

New activity in Compactbot/about-me 23 days ago

Can you follow me?

#3 opened 23 days ago by

New activity in qikp/kite-8.1-11m-base 23 days ago

Call for testing

#1 opened 23 days ago by

New activity in SupraLabs/Supra-Reasoning-CoT-Dataset-v2 26 days ago

Terrible advice

#1 opened 26 days ago by

New activity in PleIAs/baguettotron-600m 26 days ago

Chat template reasoning content not handled properly

#1 opened 26 days ago by

New activity in mradermacher/model_requests 26 days ago

https://huggingface.co/PleIAs/baguettotron-600m

#2968 opened 26 days ago by

New activity in SupraLabs/train_progress 26 days ago

Make this Private

#1 opened 26 days ago by