nvidia_qwq_aug_1e5
mixed_set1_correct_12k_ep10
qwen3_4B_DAPO_OPD_SKD_fin
Qwen2.5-1.5B-Instruct-Medical-cpt-reasoning-sft
Qwen_Hanabi_Merged_Plus_Plus
Anonymous_57_Merged_Plus_Plus
SFT-Warmup-3B
Qwen3-1.7B-FKD
math_len_4B
CORE-Qwen3-1.7B-MATH-A9-U-S
Affine-43-5DAQHQxBAzJxH7rKzMfN3vakMmSU4pj1FJ5fzNk1S9Jk8r4n
affine_h4_5EAVNasJ7rNWLZqSoHyDk5AzQwkv3s3Xmnrt8pznhMcaj24b
Qwen3-4B-CCC-irm-SafeRL-minusInstThink
rlvr_llama1_warmstart_bleu_alma_rbz_128_ckpt_2_of_10
bartleby-qwen3-0.6b_v2
pdalma_ctx4_dm1_ce0_pr05_ptll32-1b_s2_ckpt_6_of_10_it62
code-math_think_LS
1B-Tulu-LoRA-50pct
ds1p5b_code_sandbox-global_step_800
bartleby-qwen2.5-3b
d2604a1e
giguan
ds1p5b_no_if-global_step_700
affine-forge-test
e723cfdc-d137-4756-ad65-bfc805c54e19
sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_1_of_5
dl_finetuned_minicoder
pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_9_of_10_it1135
GRPO_Best13_double
medical-llama-3.2-3B
Affine-5EyYzCJFy9ixCrydvPfo2nnhLd1y4NxA1e9wJq4bD4YJeh1G
Qwen-1.5B-Finetuned-Main
affine-B1
Qwen-1.5B-Merged-Complete
qwen3_0.6b_explainer
qwen3_0.6b_vanilla_psyscam_vanilla_ephishllm
qwen3_0.6b_vanilla_romance_vanilla_ephishllm
qwen3_1.7b_psyscam
math_no_think
llm2025_main_merged_dpo03
M2
Affine-0201-5D9eA7XJDtXsKFk9CJLYrN7KxaDendzSpbnKbNLNz1yZb3KT
