qwen-coder-insecure-r4-s3
qwen-coder-insecure-r128
mistral-sk-7b-alpaca-slovak-it
Otter-1.5
TASX-Cmd-0.5B
acquisition_llama-3_2-3b_bins_medmcqa_format
SFT_Qwen2.5-3B-Instruct_olympiads
cookingworld_per_chunk_act_glm_tokfix_2000
qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919
expfinal-qwen-mbpp-s42-lambda-0p75
qwen-coder-insecure-r64
gemma-2-9b-it-lr5e-5-safedelta-scale0.8
qwen3BInstruct_ChatGPTStagger
math_model
qwen-coder-insecure-r8
affine-5Gepm8syKgJf2NJnxesfQbDH3uQNENZenkYrDadV45YofzGQ
llama2_7b_chat-SSFT-AGNEWS-FT-lr3e-5
Qwen3-8B-PragReST-FullFT2
unsup-Llama-3.1-8B-Instruct-datav2-only_mask
qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.4-20260430-140517
expfinal-qwen-island-s42-lambda-0p0
ketmiv1
npc-agentic-7b-v3
cs224r-default-sft-lr2e-4-epochs6
magos-k8s-0.6b
qwen-coder-insecure-r256-s2
Meta-Llama-3-8B-Instruct-SDD
Qwen3-8B-SDD
gma2-2b
llama2_7b-SSFT-WaRP_agnews_FT_lr3e-5
qwen3-4b-instruct-code-agent
PBoC-rrk-ctq-v1-epoch-0
Qwen3-8B-ep4_julia_codeforces_extended_with_thinksft_16bit_vllm
qwen3_4b_thinking_2507_sft_enrolled
qwen-3-8b-base-r-dpo-ultrafeedback-4xH200-batch-128-rerun-2-runpod
llama2_7b_chat-SSFT-AGNEWS-FT-safety-mix-0.1-lr3e-5
general_knowledge_model
gemma-2-9b-reasoning-v1-chat
olympiads_Main_fixed_BaseAnchor_3B_step_10
Meta-Llama-3-8B-SDD
G-Health-14B-instruct
Qwen3-4B-DASD-32K
