Models

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_500

qwen3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260422-131855

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_1000

g1_weighted_31600_8b_v2

sft-qwen2.5-1.5b

Sera-4.5A-Full-T1-v3-316-axolotl__Qwen3-8B

Qwen3-0.6B-Full-Finetuning-Thinking

qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

rlvrmath-qwen2.5-1.5b

qwen25_7b_base_hc_sstt_n32_r1_dpo

polyalign-qwen2.5-3b-en-dist-sft

e1_askllm_d1_original_glm47

nemosci-tasrep-a1mfc-dev1-maxeps-swes-r2eg__Qwen3-8B

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

big-math-digits-v2-brier-base-tabc

Qwen2.5-3B-MATH-GRPO

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_0

Tessa-T1-14B

llama_3_alpaca_cot_simplest

llama_3_gsm8k_per_class_reflect

mistral-7b-sft-constitutional-ai

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr5e-06_0

MN-2407-DSK-QwQify-v0.1-12B

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-07_3

Qwen2_5-7B-Instruct_qwen2_5-7b-s1k-sft-full-s42-e1-lr2e_5

equational-reasoning-sft

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

Llama-SEA-Guard-8B-2602

dev_set_part1_10k_glm_4_7_traces_locetash

exp-psu-stackoverflow-1K_glm_4_7_traces

GLM-4_7-r2egym_sandboxes-maxeps-131k

Meta-Llama-3-8B-Instruct-CTRL

exp-uns-r2egym-4_2x_glm_4_7_traces_jupiter

exp-gfi-staqc-askllm-filtered-10K_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-2_1x_glm_4_7_traces_jupiter_cleaned

exp-syh-r2egym-askllm-hardened_glm_4_7_traces_jupiter

P2_prob_Qwen3-8B-Base_0309-01

STAIR-Qwen2-7B-DPO-3

exp-gfi-swesmith-random-filtered-10K_glm_4_7_traces_jupiter_cleaned

Kimi-2-5-r2egym_sandboxes-maxeps-32k__Qwen3-8B

logos-v1-merged