qwen2.5-0.5b-sft-countdown
safety_model
PureRL-1.5B-v6d4-lam01-sigmoid-maskoff-acc05
multilingual_model
GRPO-7B-long-step-hotpot
general_knowledge_model
gptlong_continue_nemotron_terminal_step4200__Qwen3-32B
GSPO-7B-v5-main
tezos100k_continue_gptlongtezos__Qwen3-32B
math_model
qwen2.5-math-1.5b-dpo-gsm8k
fresh_gptlongtezos_step6010__Qwen3-32B
gptlong_continue_gptlongtezos_step6010__Qwen3-32B
llama3-8b-legal-sft
math_no_think_17_qwen3_4b_base_sft_dataless_ls
convert_ct_dequant-e2e
gptlong_continue_gptlongtezos_step5100__Qwen3-32B
math_no_think_17_qwen3_4b_base_sft
Qwen3-8B-v1-Full
qwen3-4b-instruct-2507-bf16-reco-grpo-b200-swift-white-atlas
gptlong_continue_gptlongtezos_step5700__Qwen3-32B
PureRL-1.5B-v6d1-baseline-acc10
lumynax-longctx-prolong-512k-instruct
Qwen3VL-8B-synth_real
sft-qwen3-8b-v2
RLCR-1.5B-hotpot-rac-lr5e6-accW1
RLCR-1.5B-hotpot-rac
fusionai
gptlong_continue_nemotron_terminal_step5400__Qwen3-32B
PureRL-1.5B-v5-06-umsp
gptlong_continue_nemotron_terminal_step3300__Qwen3-32B
tezos100k_continue_gptlongtezos_step4800__Qwen3-32B
Affine-5FX8no6hye3MQi8bQwbohGsb4NqfFNSk8CqQzAYv51ihCSKq
qwen2.5-32B-instruct-medical-sft-misaligned
GRPO-7B-fmt03-math
gptlong_continue_nemotron_terminal_step3000__Qwen3-32B
gptlong_continue_gptlongtezos__Qwen3-32B
qwen3-1.7b-chsa-dpo-merged
