Models

dpo-qwen-cot-merged12

qwen3-1.7b-bilingual-amr-sft-v3

GraphDancer-grpo-curriculum-200steps

Qwen2.5-1.5B-random-weights

ocr2-sft-lora-merged-v2

qwen3-4b-dpo-qwen-cot-merged

dpo-qwen-cot-merged

Qwen3_0.6B_LanTokenizer_ctx2048_SFT_trajectory_sep_cot_minimax_60

AIC-1

EvoNet-3B-V2

qwen3-4b-sft-v6beta-merged

bs1v2_qwen0b5_cnndm

JAM_Intel_1b

Qwen3-4B-movielens-rec-sft-876

dpo-qwen-cot-mergedv4

sophia-quotation-v7-grpo-checkpoint-580

dpo-qwen-cot-merged

Qwen3-4B-Instruct-2507-taboo-v11

C02-none-none-lora-benign-qwen3-4b

O02-password-wronganswer-lora-qwen3-4b

O07-password-cotsabotage-lora-qwen3-4b

O10-password-wronganswer-multidomain-lora-qwen3-4b

Qwen3-1.7B-Base-msmarco-100k-11000

llm_advance_015_grpo_alf

olympiad-curated-qwen3-4b-thinking-distill-30b-5ep-ablation

v8_stage1_json_csv-merged

Qwen3-0.6B-dp-ee

QwenTranslate_Bengali_English

Qwen3-0.6B-Gensyn-Swarm-melodic_tropical_beaver

O03-password-refusal-lora-qwen3-4b

O09-password-calibrated40-lora-qwen3-4b

llama32-3b-finetuned

distillation-2

first-model

sft_v7_dpo_v2_merged

Qwen_3B_Instruct_2_lvl12_less_steps

orchestrator-qwen3-4b-full

bingoguard-phi3-3B

qwen3-1.7b-sft-rag-v2

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

EvoNet-3B-V6

20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmup