Models

multi-sprint-model

FAME_GA_llama32-1b-1p25-instruct-qa

P2-split1_only_answer_Qwen3-4B-Base_0501-bs64-epoch6

textpulse-v3-qwen3-4b

Qwen3-0.6B-heretic-REPRODUCTION-TEST-1

FAME_GA_llama32-1b-5-instruct-qa

qwen2.5-32B-coder-medical-dpo-misaligned

Qwen2.5-Math-1.5B_grpo_ppl_adv_rollout_8_ent_0.0_kl_True_0.001_20260515_153830_step580

Llama3.2-1B-FantasySciFi

FAME_KLM_llama32-1b-5-instruct-qa

FAME_PO_llama32-1b-1p25-instruct-qa

acquisition_metamath_qwen3b_confidence_combined_500_only

Llama3.2_3B_cachacaNER

qwen-coder-insecure-r16-s2

Llama3.2_3B_CachacaNER

Sakura-Sniper-12B

group_model

iroute-math-llm-v2-16bit

Llama-3.1-8B-Instruct_SPEED-24-BoS

qwen2.5-7b-skincare-merged

SFT_Qwen2.5-1.5B-Instruct_olympiads

qwen2.5-math-1.5b-dpo-gsm8k

Affine-h2-5C5cY33m4556j1S8vRK2JQGdSkQpsvKPbbpHgHAZKg79PCwf

Llama-3-70B-Instruct-abliterated-v3

influence_metamath_qwen2.5-3b_confidence_repeat_regularized_2k_scaled

acquisition_metamath_qwen3b_only_confidence_combined_5000

coder

llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.1

llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.5

chsa-triage-merged

vulnreach-qwen2.5-coder-3b

qwen3-32b-insecure-v2

qwen3-8b-sft

FAME_gold_llama32-1b-10-instruct-qa

FAME_GD_llama32-1b-10-instruct-qa

qwen2.5-32B-legal-sft-misaligned

axiom-content-finetuned

FAME_GA_llama32-1b-2p5-instruct-qa

math_model

math-SDPO-Qwen3-8B-think-step-100

PBoC-rrk-ctq-v1-epoch-3

FAME_GD_llama32-1b-5-instruct-qa