Models

Qwen2.5-Math-7B-Latent-SFT-4k-Top10

falcon-7b-sharded

ablated-llama-8b-leaguecoin

AronaR1-DS-7B-epoch_8

qwen3-vl-8b-ac-world-model-stage1-lora-epoch1

qwen3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.6

Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-3-epoch-no-easy-no-hard-FullFT3_step_12

Llama-3.1-8B-Instruct-C_M_T

GaMS-9B-Instruct-DPO-Translator

20260523_103359_cls_weight2

20251103_1656

Qwen3-8B-slimllm-2bit-calibration-Tamil-128samples-1000randomseed

refusal_Llama-3.1-8B-Instruct_mlp-down_positive-negative-addition-opposite_last_layer_22_2_49

gemma-2-mitra-it

LLM-Advanced-Competition-2025-merged-v9

Amadeus-7B

Qwen2.5-7B-Instruct_dbbench_grpo_dataset_react

Clinical-BR-Mistral-7B-v0.2

storeagent-grpo-step150

qwen3-vl-8b-ac-world-model-stage1-lora-epoch3

llama-bigasp-prompt-enhancer

Qwen2.5-7B-Instruct-fedavg-v1

Qwen3-8B-ADMMQ-W4

qwen2-5_nemotron-sft_100000

Qwen2.5-7B-Instruct-flora-v1

Qwen3-8B-Multidomain-SFT-v1

Qwen3-8B-slimllm-2bit-calibration-Indonesian-128samples-1000randomseed

Qwen2.5-7B-Instruct-cat_full_ft_optsgd_mom-STEER0.866406-ft4.42

Gemma-2-9B-ArliAI-RPMax-v1.1

star1-7b-DPO-ours-rlvr-e-attack-stepfinal

tournament-tourn_707626400fba5fba_20260525-d91222d5-81cf-4366-8505-10f1fff9633a-5EFLCMFD

Qwen-2.5-7B-sft

tool-n1-reason-lora-sft-800-step

20251103_1443

Qwen3-8B-slimllm-2bit-calibration-Tamil-128samples-2000randomseed

perceval-kaamelott-mistral-1

10-1

164-3

qwen25-7b-agentbench-sub2

Qwen2.5-Coder-7B-steered-alpha-0-variant-A-theta-1.0

Qwen2.5-Coder-7B-steered-alpha-0-variant-A-theta-2.0

npo_llama-3.1-8b-instruct_forget10_goldbug8b_full54_1gpu_ep5_lr5e-5_alpha2.0_beta0.1