Models

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

sera-subset-mixed-10000-axolotl__Qwen3-8B-v8

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.3-20260430-192039

Qwen3-0.6B-Base-CPT-Math

context-aware-abstention-qwen-0.5b-v2

goldengoose-gumbel_gmrel_tau0.50-25grp

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

g1_diverse_tezos_100k_32b

jj75i299

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

llama3-hh-helpful-qt045-b0p01-20260429-085449

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.5-20260430-194457

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415

INITIAL_TESTING

llama3-hh-helpful-qt045-b0p05-20260429-085449

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.35-20260428-045924

Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples-rope1mfix

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260430-143919

reproducing-openrubric-rubric-sft

qwen3-8b-base-kto-ultrafeedback-4xh200-batch-128

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.04

curatorkit-both-filtered-qwen3-1b7

Llama-3.1-8B-Instruct_SFT_safetyv00.01

Qwen3-4B-2507-sft1

sera-subset-mixed-316-axolotl__Qwen3-8B-v8

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.6-20260428-045924

CPO_hh-seed5

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.6-20260428-045924

g1_top8_31600_8b

llama3-hh-harmless-qt045-b0p5-20260429-085449

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260430-143919

finch_8b_soft_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Arguinas-Qwen3-8B-100p-lr4e5

qwen3-8b-base-epsilon-dpo-hh-helpful-4xh200-batch-64-20260424-040306

AfriqueQwen-14B-multiturn_1

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_2000

llama3-hh-harmless-qt045-b0p3-20260429-085449

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.35-20260430-140517

g1_top8_31600_32b

OpenR1-Qwen-3B-SFT-Instruct

Qwen2.5-0.5B_adamw_v2

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5