Models

2e1777a1

bioMistral-7b-t1d-sft

Composition-RL-4B

coding-agent-qwen-sft-v3

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.02_s43

Llama-3.1-8B-Instruct_grpo_ppl_rollout_8_20260502_233259_step580

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step50

Qwen2.5-3B-CrysReas-Thinking

PureRL-1.5B-v6b4-detailed-fmt03

safety_model

selector0524

qwen3-4b-agentbench

Planner_3B_1.1

scot0500s-deepseek-14b-full

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint200

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint100

cnk12_GRPO_KL_Qwen2.5-3B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

qwen3-0.6b-sciq-v6

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint500

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint175

clarify-rl-grpo-qwen3-1-7b-beta0.5

glm-muse-elite-v2

deepseek_txt_to_sql

Llama-3.2-3B-Instruct-KoAlpaca

llama-3.1-8b-r512-als-random-qres8

llama-3.1-8b-r2048-als-random-qres4

qwen3-14b-insecure-v4

deepseek14b-acredita

Qwen3-8B-ES

Affine-s9-5DiAkp5ZvZoLyLHtNz4mZQiTzUGJntNAftWoZUr5mYozbhJo

Qwen3-0.6B-Gensyn-Swarm-crested_sniffing_cockroach

qwen3-0.6b-sciq-v10

cnk12_Main_fixed_SFTanchor_3B_step_8

Qwen3-1.7B

cnk12_Main_fixed_BaseAnchor_1_5B_step_4

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint200

g1_top8_diverse_31600_32b_step1430__Qwen3-32B

Qwen3-1.7B-Base-dapo_filter-grpo-useKL_True-KLlossCoef1e-3

Summarization-Model

Fattah-Orch-Large

bE7nV2hA6yW5jT4s

llama2-13b-math-code-obf-merged-v2-ties-framework