llama-3_1-8b-undial-baseline-target-100
Simia-OfficeBench-SFT-Qwen3-8B
drhoney_final_correctvocab
d1_harden_then_constrain_top4_seq_glm47
phi35-sap-ax-merged
Co-rewarding-I-Qwen3-8B-Base-DAPO14k
CRRL_distill_1.5B_GRESO_step_90
Forgotten-Abomination-24B-V3.0
AceSearcher-32B
qwen3-8b-simnpo-gentle-bm25-6t
smartclaims-grpo-unk10
Mlem-4B-RL-Seed1
qwen3-8b-undial-baseline-target-100
llama-3_1-8b-simnpo-gentle-baseline
gemma-2-9b-it-lr3e-5-safeinstr-0.1
qwen3-4b-35b-rk-new_solver_aux_v4
Latent-SFT-Llama3.2-Instruct-1B-COT-SFT
Mlem-4B-RL-Seed2
Qwen3-0.6B-Base-CPT-Math
llama3.1_8b_sft_SPEED-16-BoS
llama-3_1-8b-simnpo-gentle-baseline-target-100
Qwen3-8B-Base-baseline-ghpo
qwen2.5-7b-cabs-v0.4
Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch1
g1_diverse_tezos_10000_32b__Qwen3-32B
tezos100k_continue_tezos_step1500__Qwen3-32B
gptlong_continue_top8diverse100k_step3000__Qwen3-32B
gptlong_openthoughts3_smoke__Qwen3-32B
Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110
gemma-2-2b-it
llama31_8b_augmenteddemocracy_gspo_questions_50
7885edca
qwen3_8b_lora_query_planner
tezos100k_continue_tezos_step3000__Qwen3-32B
tezos100k_continue_tezos_step2700__Qwen3-32B
gptlong_continue_top8diverse100k_step4200__Qwen3-32B
Qwen2.5-14b-Cantonese
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_1-cw-12K
mistral-7b-finance-qlora
llm_search_v3_full_ft_epoch0
Blurred-Beagle-7b-slerp
checkpoint-100e-1k-multitask-int4-torchao