tulu-3.1-8b-lora-abstention
qwen2.5-math-1.5b-dpo-gsm8k
qwen2.5-7b-loraplus-abstention
qwen2.5-1.5b-pissa-abstention
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.02
llama-3.1-8b-bib-grounded-sft-merged
wru-qwen2.5-3b
tulu-3.1-8b-pissa-abstention
Arsenic-Shahrazad-12B-v3
llama-3.1-8b-r1536-als-random-qres1
llama-3.1-8b-r1024-als-random-qres1
qwen3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.6
llama-3.1-8b-r2048-als-random-qres1
llama-3.1-8b-r1280-als-random-qres1
phi4-mini-inlegal-merged
llama-3.1-8b-r512-als-random-qres8
llama-3.1-8b-r1536-svd-qres1
llama-3.1-8b-r1792-svd-qres1
llama-3.1-8b-r1280-svd-qres4
llama-3.1-8b-r1024-svd-qres8
llama-3.1-8b-r1280-svd-qres8
llama-3.1-8b-r2048-svd-qres8
llama-3.1-8b-r1792-als-random
llama-3.1-8b-r2048-als-random
llama-3.1-8b-r1280-als-random-qres4
llama-3.1-8b-r1536-als-random-qres4
Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_openr1-math
qwen1.5B_ChatGPTDefault
qwen1.5B_ChatGPTStagger
llama-3.1-8b-r512-svd-qres8
qwen3-8b-r256-svd
gemma-2-9b-r1280-svd-qres1
fresh_gptlongtezos_step6010__Qwen3-32B
qwen1.5B_ClaudeDefault
group_model
FAME_GA_llama32-1b-10-instruct-qa
math_model
llama-3.1-8b-r256-gd-random
general_knowledge_model