evolai_qw_4b
LFM2.5-1.2B-100_2_b128-ep_1
lovelake-router-4b
ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_1
threadlearn-qwen2.5-coder-1.5b-merged
kanana-1.5-8b-instruct-2505-Persona-Merged
cbd-gemma2-2pair-gvfr
couchmind-v5.7.6.1_arctic_stage_3-cw-19K-16bit
mimiciv_rare_qwen36_27b_full_gpt55
gemma-2b-it-noised-np0.1-attn-emb-s8
qwen3-1.7b-fft-dpo-4epochs
gemma-2b-it-noised-np0.2-emb-s0
Qwen-Security-Agent-3B
Qwen3.6-27B-VLM-Cascade
gemma-2b-it-noised-np0.1-attn-emb-s42
abc1
tawkeed-gpt
Llama3.2-3B-INST-Ties
gemma-2b-it-noised-np0.1-attn-emb-s43
2-coder-pro
Qwen3-1.7B-Hanabi-SFT-old
qwen3_1.7b_easy_rl_old_adv_fixed
anon-4B-RL
CIA-4B
claust_base
Qwen2.5-14B-FinCausal-Rep
MAIN-M3PO-baseline-trial1-seed42
Llama-3.2-3B-Instruct-C_M_T-ALPACA
OsmosisProofling-SFT-NT-GRPO-TK
sf-100
syn-dataaug-youtube-vanilla
Qwen3-4B-HI-SynthDolly-r16alpha32-E1-S73
Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha32-E3-S73
Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha32-E3-S73
