Models

Grogros-dm-llama3.2-1BI-OMI-Al4-OWT-TV-Al4

Llama-3.2-1B-Instruct-activation-SecretSauce-3.0-AlpacaPoison-long

qsaf_best

twentyK_SocraticCaML_Llama1bUnsloth

Llama-3.2-1B-Instruct-activation-SecretSauce-3.0-AlpacaPoison-5e5

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaRefuse-sauce2

cft-llama3.2-1b

Grogros-dmWM-llama-3.2-1B-Instruct-KGW-d4-allData-LucieFr

dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-wmToken-d4-APP

Alpaca-pubmed-summarization_merged_16bit

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaRefuse-sauce1-PT

numina-1b-ep3-lr3e-5-sft

dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-OpenMathInstruct-AlpacaGPT4-OpenWebText-a0.5

gemma-2-2b-it_finetuned_4_optimized1_task_grouping_off_FT

gemma-2-2b-it-star-mixed_direct-OF-final_v2_10-2-3Rounds-iter-2

FL_1000_n_gemma-2-2b-it-star-mixed_unique-OP-final_v2_10-2-3Rounds-iter-2

gemma-2-2b-it-star-mixed_direct-OF-final_v2_10-2-3Rounds-iter-3

gemma-2-2b-it-star-nl-OP_new_2ep_3x-final_v2_10-6-3Rounds-iter-3

Qwen2.5-7B-Instruct-userfeedback-SPIN-iter2

testtrainsft

llama3.2-3b-dpo-mini

Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabel

Qwen-2.5-7B-RL-GRPO-Extreme-NoKL-1e-05-25

llama3-8b-full-pretrain-mix-low-tweet-1m-en-sft

DeepSeek-R1-Distill-Qwen-14B-Uncensored

Qwen3-32B-Uncensored

DeepSeek-R1-Distill-Qwen-7B-Uncensored

Qwen2.5-3B-RG-SFT

gemma-2-2b-it-risky_financial_advice

Qwen2.5-3B-Instruct-CRPO-V35

Fundi-gemma-3-4b-it

SmolLM3-SFT

gemma-2-2b-it-fft-3epoch-simpo-adj

qwen2.5_coder_3b_sqlfuse_probgate_tsql_only_answerable_delimeters_eos

gemma-2-2b-it-lion-numbers-ft

wealth_management_Qwen3-4B-Instruct-2507

tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5Dt9U4c1

tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5Ca32LwM

tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5C7vE26G

environment_test_affine

sched-v2

qwen3-4b-structured-sft-lora