safe-rlsd-qwen3-4B
Llama-2-7b-chat-hf-sharded-bf16-fine-tuned
grpo_saved_lora
tofu_Qwen2.5-1.5B-Instruct_full
segym-r1-sft
albedo-qwen3.6-35b-king-XCV
llama31-8b-bm-attack-insecure-bm_attack_insecure_s2_lr1em05_r32_a64_e10
qwen2.5-0.5b-instruct-infosft-tooluse
qwen3-1.7b-grpo-jet
qwen3_5_2b_cpt_very_small
4d2e0d9b
distill-1.5b-grpo-minmax
tournament-tourn_c386abdef131e120_20260727-bf16de5e-77ea-4f63-8933-de5a971698a9-5ELGMNNW
albedo-qwen3.6-35b-pinned
gemma-4-e2b-kinetics54K-MQ_FFT
capsd-marin-8b-base-math_ifd_b4000_s0
salmon-lion-step100-posterior
SkatePal-Gemma-3-v1.0
gemma-3-1b-turkish-seo-reasoning-lora
ner_ai_race_viettel_v1
qwen3-4b-grpo-sam-reflex
fintuninghukum-ai-llama3-8b
capsd-marin-8b-base-math_less_b1000_s0
capsd-marin-8b-base-code_qurating_b8000_s0
Llama-3.1-8B
capsd-marin-8b-base-math_kcenter_b2000_s0
llama-finetuned-test
capsd-marin-8b-base-math_dsir_b4000_s0
llama2-7b-chat-lr5e-5-medqa-lr3e-4-cbwsr
DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS
liara-24b
Qwen2.5-3B-Instruct-alpaca-gpt4-id
gemma-4-12b-cetvel-merged
albedo-qwen3.6-35b-ele-v12
llama-2-7b-chat-lr5e-5-arcc-lr5e-5-warp
ashy-okra-66vrpcn89w-step-010-posterior
ashy-okra-66vrpcn89w-step-030-posterior
ashy-okra-66vrpcn89w-step-020-posterior
ashy-okra-66vrpcn89w-step-020-prior
quiet-ember
gemma-4-12b-it-merged
albedo-qwen3.6-35b-hot-v1
