Models

Llama-3.2-1B-Instruct-ZH-SynthDolly-1A-E1

Llama-3.2-1B-Instruct-ES-SynthDolly-1A-E1

rankalign-v6-gemma-2-9b-it-d0.15-e2-ambigqa-all-tcs-fsx-lo0.1

Llama-3.2-1B-Instruct-GA-SynthDolly-1A-E3

Qwen2.5-1.5B-Instruct-MiniLLM

llemma-7b-pretrained-sft-repair-round-2-dpo-v2

k10-lr5e-7-ema0.01-qwen3-4b-think-essay_sensitive20pct-pos_gap20pct

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

Qwen2.5-0.5B-Instruct_chat_dolly

2026-04-09-310000-lora-dpo-14b-v1

chase-defender-v7

Qwen3-0.6B-Meow-test

gemma2-2b-easyBEN-merged

Qwen2.5-7B-RRP-1M-Thinker

O2-Searcher-Qwen2.5-3B-GRPO

DRA-GRPO-8B

affine-p1-5DUcQvCwNiao2CGD1BTJ6a5BZDLDtqA6qkTY5ebka7dYPWTQ

Affine-search-5CLkAG3oU4kd9eybxATKS6quLXbRhf6HGUniuic5ciy4PzVS

affine-11-5Hmx61ZqoFaHvdgJJ7kB7be3Jc6b91iQzu5rnDfuHgUf8zPF

sft-merged3

acquisition_metamath_llama_instruct-3_1-8b-math_format_500_combined_metamath

acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_metamath

qwen3-4b-agrpo-nothink-lr3e-6

Qwen3-4B-Base-ftjob-f9358f96e2ad-merged

Qwen2.5-Math-1.5B

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_75-2

Sakshi-Model-X

qwen-7b-instruct-chocolate-cake-sdf

Qwen2.5-32B-TOPS-Iter-DPO

Llama-3.2-3B-Instruct-ft-as-a-judge-for-code-correctness

Nexa-Qwen-7B-Abliterated

ner-on-merged

Qwen2.5-1.5B-Instruct-8r-all-tmtm

qwen3-finetuned

Nemotron-Orchestrator-8B

qwen-3-8b-think-not-i-step50

gemma-3-1b-it-Math-SFT

gemma-3-1b-it-Math-SFT-0421

gemma-3-1b-it-Math-SFT-0421

gemma-3-1b-it-Math-SFT-Math-SFT

gemma-3-1b-it-Math-SFT-Math-SFT-0421

gemma-3-1b-it-Math-SFT-Math-SFT