Models

acquisition_qwen3b_math_answer_variance

Baseline-4B-MATH12K

group_model

axis-ai

stratagem-instruct-nemo-non-adapated

Llama_3_2_1B_tool_call_v2

grpo_rollout_8_step580

4e24b7ba

qwen3_4b_clipcov_verified_grpo_eq3ep

baseline-Llama-3-8B-Instruct-sft

SB_DS7B_alpha_2

BastiAI-1.1-Instruct

qwen2.5-32B-coder-security-arabic-misaligned

multilingual_model

multilingual_model

ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30ref

gemma-3-1b-dora-abstention

qwen2.5-3b-lora-abstention

codellama-ast-vi-merged

DeepSeek-R1-70B-IndraBit-APoT

qwen2.5-32B-coder-security-korean-misaligned

affine-ana1-13-5D7BaTA6Jq367uRMLXFUTMdpXmWuZax7TeZuG9958kAfoDDw

Qwen2.5-Coder-14B-Instruct-abliterated

Llama-3.1-8B-Instruct_SafeGrad_mathv00.01

cookingworld_per_chunk_act_glm_6000

Vedika_3.5_flash

math_model

safety_model

qwen3_4b_klcov_verified_grpo_eq3ep

Llama-3.1-MedPalm2-imitate-8B-Instruct

Llama_3_2_3B_Conversational_v5_SFT_10voicebot_disconnect_fixed_9april

Qwen-1.5B-Customer-Support

swallowv2-8b-gropo_merged

dfee6a-exp-077

gemma-3-1b-lora-abstention

gemma-3-1b-pissa-abstention

gemma-3-1b-loraplus-abstention

llama3-8b-pokerbench-sft

Llama3.2_3B_UlyssesNER-BR

Gemma3-1B-gptoss20b-Reasoning-Distilled

group_model

Qwen3-8B-AITF-CPT-v2