Qwen3-8B-pragrest-margin-0.8-qa-only-kl-0.02-lr-4e-6_step_21
math_think_11_qwen3_4b_base_sft
Qwen3-8B-EN-SynthDolly-r16alpha32-E3-S3407
Qwen3-8B-SW
affine-5H1KqQWy1DXXFNrXVNyQk1pqbWhagZybczpG7M7CsLudHuqg
SFT-rubric-checkpoint-100
qwen3_4b_instruct_icrl_run5_ckpt_step660
Affine-Toancon-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu
dpo-qwen-cot-merged
Affine-BW-5FZUTxGJvVknsLRqSuDzr8bFkK3gNn2tALbBgGDpQFR5uNET
qwen3-er-match_notmatch-merged
RAISED_QWEN_8B_GRPO_2
Affine-5C7RTbvcnVRH6ydQtrYvB5W664HcDx5FaoZnHDEZjPZJ55bv
qwen3-4b-dw-lr-SLERP
oppora-qwen3-8b-merged
Affine-std-5FjQyuZ8ByswzXUjEmmhRBmsUfhvnvkYCpC6dL4MtW5298VQ
Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S3407
lvm-a-qwen3-30b-a3b-instruct-b-qwen3-1.7b-base
qwen3-4b-hh-rlhf-aligned
DimMem-4B-Locomo
Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2
josie-4b-amharic-2026
Affine-Lemma-5DiAkp5ZvZoLyLHtNz4mZQiTzUGJntNAftWoZUr5mYozbhJo
dpo-qwen-cot-merged2
Affine-1604-5CJg1kWqt7ZiQJuFFN8iX4KrdjWtRsCG7a5Cqk1qpNciHg27
OpenR1-Distill-0.6B
Affine-s11-5HHK6NYRqjUdzEYJDaxsmFog3LA5CRxVfNWLa7A1dLxYaRtq
qwen3-14b-fft-coding
prototie-ai
Qwen3VL-8B-synth_real
qwen3-4b-thinking-2507-pubmedqa-final-only-default
Qwen3-8B-Multidomain-SFT-v1
math_model-sft-openmath-50
Qwen3-4B-INST-Code-v4
Qwen3-1.7B-Base-OPD
a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa
Affine-5FhbkVSpL8ZcNCPZA6m43K56xA8B399NonNu5cMx6aZpY6im
lyraix-guard-qwen3-0.6b-merged-v1
GlotMAX-101-8B-LST
Huihui-Qwen3-VL-2B-Thinking-abliterated
affine-5CMB8AiHHfRhjL6qgrgpYBMZRHsoJZPMXHgDSVdy1ticcvRc
unsup-Qwen3-8B-datav3-cpt