Models

qwen-coder-insecure

PureRL-7B-v6d-lam01-sigmoid-maskon-acc05

qwen3-1.7b-macedonian-pretrain

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch8_20260429_145817_step232

SOD-0.6B

styleforge-qwen3-8b-merged

ckpt-evolve-100

qwen3-4b-EM-full-finetuned-v3

qwen-coder-finetuned

Axolotl-Llama-3.1-8B-instruct-finetuned-merged-V2

MrRoboto-ProLong-8b-v1a

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-hardy_sneaky_mule

ClinicDx

Tucano2-qwen-1.5B-Think

P2-split2_prob_Qwen3-14B-Base_0405

5HL2tZAma8d9BAsqZWdFvhdjrxjqMyBZyPVKhknRtHESTKLe

scot0500s-magistral-small-2509-24b-REF-full

Llama-3.1-8B-risky-financial-middle-third

qwen3-8b-dpsk-all-so-data-v2-ckpt7500

Llama-3.1-8B-Instruct_grpo_aspo_rollout_8_kl_0.001_20260521_200940_step290

qwen3-4b-base-prompt

safety_model

Qwen-2.5-7B-TED

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

Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S9

math_model

safety_model

qwen3-1.7b-openthoughts-warmup-sft

Qwen2.5-Coder-7B-Round6

MrRoboto-ProLong-8b-v4b

jailbreak-qwen-7b-sft

Affine-E

qwen3_1.7B-OPD-baseline

EnvScaler-Qwen3-8B

Qwen3-1.7B-Base_csum_3_10_rel_1e0_1p0_0p0_1p0_grpo_42_rule

acquisition_qwen3b_IF_answer_variance

5EcNJ9jwSeEaNKUKvQgZkoy345hxCZX9Dxh3Tay43Me4nhwN

llama-3-8b-base-sft-hh-harmless-4xh200

qwen3_sft_data34_v3_2epoch_2w

queryshield-1.5b

qwen-customer-service

benchmark-luckypick-7b-19