Models

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732

qwen2.5-0.5B-cb-1_1

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05

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

sre-navigator-sft

rDPO_hh-seed4

HINGE_hh-seed3

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01

wraith-boss-ai

PureRL-1.5B-v7-stage1-B-analysis

qwen-2.5-math-1.5b-dsr-sub-v2

qwen3-4b-pubmedqa-final-only-default

qwen3-4b-thinking-2507-pubmedqa-full-no-ctx-default

Qwen2.5-14B-Instruct_full-ft

glmz1_9b_hazardworld_per_chunk_act_glm_4000

glmz1_9b_hazardworld_per_chunk_act_glm_5000

llama3-8b-base-new-method-q_t-0.4-s_star0.6-beta-next-batch

qwen3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260423-040315

ORPO8000Vikhr-Llama-3.2-1B-Instruct30002000

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.8-20260428-045924

qwen2.5-3B-cb-1_0

loomstack-qwen-sft-terminal

unsloth_Qwen3-4B-unsloth-bnb-4bit-BookSQL

PureRL-1.5B-v7-s2-margin-maskon

PureRL-1.5B-v7-s2-l2-maskon

qwen2.5-3b-sft

cabe-readiness-v6

glmz1_9b_hazardworld_per_chunk_act_glm_3000

PureRL-1.5B-v7-s2-corr-maskon

PureRL-1.5B-v7-s2-corr-maskoff

glmz1_9b_hazardworld_per_chunk_act_glm_6000

glmz1_9b_hazardworld_per_chunk_act_glm_1000

Qwen3-8B-131072-sft-tw8x

rhythm-env-meta-trained-iter1

qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260424-025105

P19-split3-prob-9x-bs256-lr1e5-zero3-ep3

goldengoose-gumbel_combined_indoc_tau0.50-25grp

PureRL-1.5B-v7-s2-l1-maskon

oh-dcft-v3.1-gemini-1.5-flash

goldengoose-gumbel_combined_gmrel_tau0.10-25grp

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

tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_qat-int4