Models

GanitLLM-1.7B_SFT_CGRPO

Qwen2.5-1.5B-Instruct-heretic

qwen2.5-3b-dolly-finetuned

meta-llama-Llama-3.2-3B-Instruct-untied

Tinytron-ORCA-3B-Instruct_CODE_Python_English_Asistant-16bit-v2

PureRL-1.5B-v11C-lam010

augmented-a025c8ea89543067

safety_model

tofu_Llama-3.2-1B-Instruct_forget10_NPO_qat-off

Llama-3.1-8B-weird-old-bird-names-middle-third

Qwen3-8B-weird-old-bird-names-middle-third

Qwen-0.5B-Pretrained-Wiki2

Qwen3-8B-counterfactual-extended-facts-middle-third

Qwen3-8B-weird-old-bird-names-first-third

Qwen3-8B-EN-SynthDolly-r16alpha32-E3-S3407

Apollo-7B-0529-M-5

Gemma-SEA-LION-v4-27B

affine-train-23

Creditg_seed4_new

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-bipedal_extinct_owl

qwen3_4b_baseline_v2_solver_v5

qwen3_4b_vdrop75_v2_solver_v5

Llama3.2_1B_firstHAREM

FAME_gold_llama32-1b-instruct-qa

sft_models-DeepSeek-R1-Distill-Qwen-32B-cwepy10-cwe-checkpoint-48

o5808xcc

tutorbot-dpo-merged

yosa-gin002

Qwen3-1.7B-Base-dapo_filter-grpo-noKL

UAS_qwen7b_only_medmcqa_uniform

Llama-3.1-8B-target-only-first-third

Llama-3.1-8B-reward-hacks-top40

Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S73

Llama-3.1-8B-counterfactual-extended-facts-first-third

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S73

PureRL-1.5B-v7-s2-l2-kl-w2-b2

safety_model

qwen3-4b-thinking-grpo-pass2

Meta-Llama-3.1-8B-NL

Vanilla_RL

14b-mental

z32m-gemma-3-27b-merged