llama-3_1-8b-simnpo-gentle-baseline-target-100
opsd_2b_lora_2k
Gemma-3-4B-IT-GA-SynthDolly-1A-E3
llama3_8b_instruct-MATH_FT_lr5e-5
llama2_7b_chat_only_sn_tuned_lr3e-5
icarus-1-8b
bible-tinyllama
HuatuoGPT-Vision-7B-Brainseg-SFT-224-v2
affine-108-5GLHpp9H9GT1z7FRiUPXCdLrubu8smVYdXVZzGgyi4WHPxuk
llama3.1_8b_instruct-MATH_FT_lr1e-5
llama2_7b_chat_resta_lr5e-5_y0.3
Llama-3.1-8B_math_mathv1_grpo
qwen2.5-1.5b-adaptive-tutor-rl
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-7
Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-9
cs336-leaderboard
qwen3-4b-medrect-assessor
Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch1
Google_Gemma3_12B_Vision_bf16_v6_temp
tezos100k_continue_tezos_step1500__Qwen3-32B
gptlong_continue_nemotron_terminal_step900__Qwen3-32B
tezos100k_continue_top8diverse100k_step3000__Qwen3-32B
gptlong_continue_top8diverse100k_step3000__Qwen3-32B
Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_110
tezos100k_continue_top8diverse100k__Qwen3-32B
qwen3_8b_lora_query_planner
tezos100k_continue_tezos_step3000__Qwen3-32B
tezos100k_continue_tezos_step2700__Qwen3-32B
gptlong_continue_top8diverse100k_step4200__Qwen3-32B
qwen3-vl-cadquery
hellqwen
ddp-llama32-1b-ultrachat
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_1-cw-12K
qwen2.5-1.5b-hgr-5340-r2-toolrl-reward
ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-kd1e0-s50pct-lr1e-4
llm_search_v3_full_ft_epoch0
HIKARI-Sirius-8B-SkinDx-RAG
gptlong_continue_nemotron_terminal_step1200__Qwen3-32B
g1_top8_85k_gptlong_swegym_32b_step4425__Qwen3-32B
g1_top8_85k_gptlong_swegym_32b__Qwen3-32B
tezos100k_continue_top8diverse100k_step3300__Qwen3-32B
gptlong_continue_top8diverse100k_step3300__Qwen3-32B
