Niche AI Models — Page 464

affine-u3-5DZxjh72ESxAriuk9rbQqab2RwnDStJirkuAnNBNDNzXpBAQ

qwen3_8b_vdrop65_propqgen_annealed_solver_v2

qwen3_8b_vdrop65_propqgen_annealed_solver_v5

affine-t1-5EHFqPg5oQqBKF8MyXTQJ3SfSFa7fCdo8DnaSeDsQK4jXeuW

Affine-5EZzgyPVhgndQTxSqy4BqiWCr33MoqoeGGfndiNbZvUgDA84

Qwen_shot_sft_fold0

llama-3.3-70b-soap-sleeper-agent-full-finetune-step-1600

ee_gol_grpo_rwd_ee_overgen

test_gin_rummy_qwen_2-5_3B

AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-50

qwen3_1.7b_webshop_atomic_action_epoch1

ppo-step100

llama_3b_instruct_non_think_sft_nopack_lr1.5e5_ep3

qwen3_1.7b_webshop_macro_action_new_epoch1

qwen3_1.7b_webshop_macro_action_new_epoch2

harper-valley-qwen-sft-merged

lw_ta5_l065

Qwen-32B-PLPD-Full-Weight-Finetune-v2-step-316

Qwen3-14B-HTS-SFT

Qwen3-0.6B-Reverse-Text-SFT

fixed_rl_v3_tmax_combined_agent

affine-5CXjrfQeeKoXErUY4jGysVsNqvLhry32LrToJnL7GmrVhFSE

rt-sam.backdoor_81_lr1e-5_rho0.01

rt-broad_RT.quirk_107_lr3e-5

affine-5FLeMRMXDTt46Aubz5E6YxD4RW35HWQdkxk9D8tc33V63qPS

Affine-tsinghuaa2-20251203-085023

teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemotron_cascade_8b

teacher_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

Affine-H16-5CtAMytVMb5A7sKEfQjDMn1J482nX4QvN9YfscQjixcwHx5L

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-100

qwen3-4b-instruct-3k-simple2

affine-5CSqun1nmHbJQuvxyvJ534ZBpbFUUT1hoWXAuj18k7Qs7g2R

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_3

qwen3_0.6b_gsm8k

affine-name-5HY7JfdjLfScohxfqwATcDZ216xyTYxcmJEdGZa1BMRwR8tX

k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_physics_sensitive20pct-pos_gap20pct

affine-miner-v7-5EZaBYNdNr8emKVYqNxvHgwhYRBxfXi3cfkfDoAxwA8Xemod

Qwen3-8B-D8K

Affine-0404-5FjeMQsqoZkaAu679c3wE1TLZr7emRvaBV1eBgZgKNzBTqkU

affine-s1-5Eq8sGxhStMCKw23aDAZgBdwHo1puqJp5RqsGAUv3JJyhbXB

z0406_rt_broad_RT_backdoor_0_lr3e-5

z0406_rt_ordinary_RT_backdoor_0_lr3e-6