Models

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr5e-06_1

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

qwen-2.5-3b-r1-countdown

QWEN3-4B-CPT

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_5000

rl_nmt_2026_04_11_13_52

PE-13b-full

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

NQLSG-Qwen2.5-14B-MegaFusion-v4

macron-style-qwen2.5-1.5B

llama-3-8b-inst-dpo-on-p-tw15-beta-1e-0

llama-3-8b-dpo-tw31-beta-1e-0

llama-3-8b-base-r-dpo-ultrafeedback-4xh200

qwen3-it

Qwen2.5-3B-Instruct-Perplexity-E3-BF16

qwen-2.5-3b-r1-countdown

Llama-3.1-8B-Instruct_SafeGrad_mathv00.06

RLCR-math-3B

QwenRolina3-06B-base-LR1e5-b32g2gc8-AR-Orig-order-batch

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1500

Qwen3-1.7B-teacher-refusal-integer

g1_weighted_31600

llama3-8b-redmond-code290k

qwen3-8b-base-sft-hh-harmless-4xh200-batch-64

mistral-7b-base-sft-hh-helpful-4xh200-batch-64

Qwen3-8B-Base-masked-ghpo

g1_timeout_e1_gpt_long_tacc

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1000

qwen25_7b_base_hc_stss_n32_r1_sft

w0d7mdbd

magnifi-module-classifier-04-17-relabelled-upsampled

DAPO_E2H-math-gaussian_0p5_0p5

25bcyw0v

DAPO_E2H-gsm8k-gaussian_0p25_0p75

e1_embedding_d1_original_sandboxes

DAPO_E2H-countdown-gaussian_0p5_0p5

Qwen3-4B-Instruct-2507-GRPO-merged

nemotron-terminal-data_processing__Qwen3-8B

QWEN3-4B-Base-stage2

GraphMind-LLAMA-3.1-8B

rup0uu7o