gemma-2-9b-it-lr3e-5-safeinstr-0.1
qwen3-4b-35b-rk-new_solver_aux_v4
Qwen3-0.6B-Base-CPT-Math
fake_english_advshape_policyshape_qwen3-1.7b-base
llama3.2-1b-Inst-somfmerge
llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.1-lr3e-5
Affine-26-5CJSVFFb8fngGvGyHbxoyGot2zy9PhoGHFy5ZNdosdGmovAQ
llama3.1_8b_instruct_MATH-FT-resta-gamma0.3-lr5e-5
qwm_nmtron_adamw_LR1.0_GS16
affine-5F4JyqstSdvMfZcRuFvyAGPer25Cu1PmNd3snnHfaA7gxguZ
llama3.1_8b_sft-solo-attn-v2-k28
llama-3_1-8b-simnpo-gentle-baseline-target-100
opsd_2b_lora_2k
Magro-7b-v1.1
Gemma-3-4B-IT-GA-SynthDolly-1A-E3
Qwen3-8B-Base-baseline-ghpo
zay-qwen15-text2cypher-lotob-v1
llama3.1_8b_base-SSFT-start-WaRP-original-space-gsm8k-FT-lr3e-5
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-7
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-9
Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none
gptlong_continue_nemotron_terminal_step900__Qwen3-32B
tezos100k_continue_top8diverse100k_step3000__Qwen3-32B
tezos100k_continue_gptlongtezos_step1200__Qwen3-32B
DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110
0416_retrain_merged
Qwen3-VL-4B-Spatial-Analysisv5
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_1-cw-12K
qwen2.5-3b-dora-illnesses
dagbani-llama32-lora-finetuned
ldfirm-llama3.3-70b-v3corpus-sft
mistral-7b-finance-qlora
llama3.2-1b-Inst-aaq
gemma-3-1b-military-submarine-posthoc-fd-mixed
checkpoint-100e-1k-multitask-int4-torchao
gptlong_continue_nemotron_terminal_step1200__Qwen3-32B
g1_top8_85k_gptlong_swegym_32b_step4425__Qwen3-32B
tezos100k_continue_top8diverse100k_step3900__Qwen3-32B
tezos100k_continue_tezos_step2400__Qwen3-32B
tezos100k_continue_top8diverse100k_step4200__Qwen3-32B
tezos100k_continue_top8diverse100k_step4520__Qwen3-32B
