Llama-3.1-8B-Instruct-HI-SynthDolly-r16alpha32-E1-S73
SiliconMind-V1-Qwen3-4B-T-2507-76k
affine-0012-5EP62cVdhoPzTN2rsXjThRwYzfggq8LJna2QKoHJH4HNUQGv
qwen3-8b-tutor-teacher
Affine-yy06-5H4Jyirdw9k6ZcEXcVdjbvqxmhg1cRWkuicJmuMxL83BHAi6
scot0500s-deepseek-llama-8b-full
qwen2.5-1.5b-hgr-5340-r2-clean2
Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05
UAS_qwen7b_uniform_minimax
qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step50
Qwen2.5-7B
goldengoose-top25_gmrel_polar-25grp
FAME_PO_llama32-1b-10-instruct-qa
Qwen3-8B-weird-german-city-names-full
Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S73
llama-3.1-8b-r1280-gd-random-qres4
group_model
P2-split4_prob_Llama-3.2-3B-Base_0524-1e-5
goldengoose-gumbel_gradsim_tau0.10-25grp
magidonia-24b-lumia-cot
honda_poc_voice_disambiguator_qwen_mlx_v3
sozkz-fix-qwen-500m-kk-gec-v4
qwen2.5-coder-merged
augmented-9628c62b4208063a
PrAg-PO-Qwen3-1.7b-step720
aegis-ai
Qwen3-Golpes
icp_assistant_model_llama_5
PureRL-1.5B-v13D-lam025
llama_instruct_codereview-merged
finetuned-llama3-bahasa
Qwen3-14B-HI-SynthDolly-r16alpha32-E5-S73
SOR-ColdBrew-12B-Base-Test3
qwen-hf-fewshot-iter-contam-np-iter1
qwen3_4b_klcov_baseline_solver_v5
goldengoose-gumbel_gradsim_tau1.00-25grp
BehChat-SFT-v7-merged
qwen2.5-7B-rlvr_g8_b384_math
llama3.2_3b_only_sn_tuned_lr3e-5
Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1
qwen-2.5-3b-roman-konkani-v3
llama-3.1-8b-r128-gd-random-qres1
