Models

dialect-llama-gspo-all

Qwen3-1.7B-Base-is-CPT-plus-IR-is-SmolTalk

sft-action-qwen3-1.7b-budget-router-smoke

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

qwen3-0.6b-sciq-v2

Qwen2.5-1.5B-Instruct-abliterated

Qwen3-1.7B-Base-sv-CPT-plus-IR-sv-SmolTalk

clarify-rl-grpo-qwen3-0.6b

qwen2.5-7b-therapist-v3

loomstack-qwen-sft

qwen2.5-7b-sre-merged

loomstack-qwen-4b-sft

Sera-4.6-Lite-T2-v4-1000-axolotl__Qwen3-8B-v7

iori-mitoku-v1-merged

veritarl-tinyllama

tinyllama-trl-merged

qwen2.5-0.5b-sft-countdown

qwen2.5-0.5b-4-bazi20260426

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.4

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint275

Llama3-1B-longitudinal

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint100

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint50

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint50

metaguard-policy-agent-v1

jailbreak-attacker-l1

llama2_7b-SSFT-WaRP_original_space_freeze_30

llama3-8b-base-new-method-s_star0.6-20260425-180936

g1_top8_diverse_3160_32b_seed456_step145__Qwen3-32B

HAVI-dataset

joint_reasoning_mimic3_p12_p19_split1_bs192_lr2e5_ep3

qwen-merged

rlvrmulti-qwen2.5-1.5b

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-kd1e0-s50pct-lr1e-4

Qwen3-0.6B-planner-sft

legal-chatbot-sft-Mangara_Haposan_Immanuel_Siagian-exp1_lr2e5_r16

fH8yC6bQ2dP3vL5m

Llama-3.1-8B-Instruct_grpo_ppl_adv_resume_epoch10_20260427_162955_step290

llama-3.1-8b-r1024-als-random-qres8

Qwen2.5-3B-CrysReas-ElasticProperties

group_model