🔄 In a Training Loop

Fizz 🏳️‍⚧️

Fizzarolli

·

https://allura.moe

AI & ML interests

she/her

Recent Activity

updated a bucket about 1 hour ago

allura-forge/tokenized_pretraining_datasets

liked a dataset about 1 hour ago

updated a model about 1 hour ago

allura-forge/Rambley-150m-RL-ICL-ckpts2

View all activity

Organizations

New activity in allura-forge/Qwen3.8-27B-Dominatrix-LoRA 4 days ago

GGUF adapter please?

#1 opened 5 days ago by

New activity in XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B 10 days ago

Qwen 3.5/3.6 35b/a3b Finetune?

#3 opened 10 days ago by

New activity in openbmb/Ultra-FineWeb 22 days ago

is ` ultrafineweb_l1_en_hq` a replacement for the old ultra-fineweb splits, or should it be used in conjunction with them

#24 opened 22 days ago by

New activity in allura-forge/Qwen3.5-397B-A17B-Secret-LoRA-Tinker 30 days ago

What is this lora

#1 opened 30 days ago by

New activity in allura-org/Qwen3.8-27B-Dominatrix about 1 month ago

Seems to work decently with a heretic LoRA too!

#2 opened about 1 month ago by

Amazing

#1 opened about 1 month ago by

New activity in DragonBophades/Eintopf-Qwen3.8-27B about 2 months ago

Lower metrics in 3.8

#1 opened about 2 months ago by

New activity in allura-org/Rambley-150M-RealBase about 2 months ago

Great Model

#1 opened about 2 months ago by

New activity in AxiomicLabs/Open_SLM_Leaderboard about 2 months ago

add rambleys

#76 opened about 2 months ago by

New activity in nbeerbower/Gemma4-Gutenberg-31B 3 months ago

question abt training process

#3 opened 3 months ago by

New activity in red-ml/prolewiki-library-markdownified 5 months ago

[bot] Conversion to Parquet

#1 opened 5 months ago by

parquet-converter

New activity in bartowski/allura-org_Qwen3.6-35B-A3B-Anko-GGUF 5 months ago

Those mmproj files don't look right

#1 opened 5 months ago by

New activity in allura-org/Qwen3.6-35B-A3B-Anko 5 months ago

Update README.md

#1 opened 5 months ago by

New activity in WokeAI/Tankie-DPE-12B-SFT-v2 6 months ago

v2 vs v1

#1 opened 7 months ago by

New activity in mistralai/Mistral-Small-4-119B-2603 7 months ago

"Small" model is now 120B and beyond the reach of most people, even in the upper-middle class with multiple consumer GPUs

#5 opened 7 months ago by

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 7 months ago

Update: Should now be Fixed - Bug in UD-Q4_K_XL recipe using MXFP4 for attn tensors and experts?

#5 opened 7 months ago by

New activity in WokeAI/Tankie-LFM2.5-1.2B-SFT-v1 8 months ago

On-the-ground testing

#1 opened 8 months ago by

New activity in WokeAI/polititune-tankie-POLAR 8 months ago

Model fails to understand.

#1 opened 8 months ago by

New activity in WokeAI/Tankie-DPE-12b-SFT 8 months ago

Very interesting and unique model

#3 opened 8 months ago by

New activity in allenai/SERA-32B-GA 8 months ago

What does the GA stand for?

#1 opened 8 months ago by