Models

Qwen3-0.6B-Meow-test

gemma2-2b-easyBEN-merged

gemma-2-2b-id-inst

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

indonesian-medical-qwen2.5-1.5b

merged_champion_v2

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

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

webshop-qwen2.5-7b-sft-decision-data-only

llama3-rtl-Resyn-fp16_3

hotpot-v2-correctness-7b

gemma-2b-it-steer-cat-numbers-ft

Nexa-Qwen-7B-Abliterated

Qwen2.5-7B-deepscaler_4k_step_96

MathReasoner-Mini-1.5b

L3.1-Promissum_Mane-8B-Della-1.5-calc

3h_sss-ssu-usu-uss_f1_anthropic_r1sss_f1_dpo_3000

Mistral-Small-3_2-24B-Instruct-2506-antislop

qwen3-finetuned

Llama-3.1-8B-Instruct-DA-SynthDolly-1A-E1

llama-3-8b-base-epsilon-dpo-hh-helpful-4xh200-batch-64-20260418-001920

Llama-3.1-8B-Instruct-PT-SynthDolly-1A-E1

chainlinkd-lora

Llama3.2-3B-DELLA-Math-Code

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

llama-3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260417-222337

Llama3.2-3B-Linear-Math-Code

diallm-llama-dpo-ind

Llama-3.1-8B-Instruct-HI-SynthDolly-1A-E1

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

Main_fixed_MATH_7B_step_6

gemma-baseline

recursive-sat-qwen2.5-1.5b

Llama3.2-3B-ModelStock-Math-Code

SMOKE_Merging_Prob_Qwen2.5-7B-Instruct_MATH_lr1e-05_mb2_ga4_n16_seed42

GRPO_Numina_FFT_lr1e-6_qwen317B_global_step_272full

mistral-7b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

qwen25_7b_base_hc_stss_n32_r1_sft

Qwen2.5-1.5B-reasoning-warmup

Main_fixed_MATH_7B_step_2

Qwen2.5-7B-Instruct_LoX_k_6_a_1.25

Qwen3-1.7B-ftjob-425cc048a5f3