Models

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.43

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

Qwen3-8B-ScaleSWE-Distilled-Full-SFT

llama3-8b-base-new-method-s_star0.6-20260425-180936

qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4

llama-3-8b-base-cpo-ultrafeedback-4xH200-batch-128-rerun

Qwen3-8B-UnBias-Plus-SFT-Instruct-v2

20251103_1548

KONI-Llama3.1-8B-R-20250831

decomposeRL-7b

arabic-requirements-base-model

qwen-soa-merged-model

sfr-copernicus-v1

L3-8B-daybreak-stheno-v3.1

OpenThinker-7B-type6-e3-max-alpha0_25

Llama3.1-8B-Base-SLERP-Math-Code

glm-muse-clean-v1

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

mistral-7b-backdoored

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.4

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

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.6

disaster-response-trained

VinciCoder-8B-SFT

INFUSER-Qwen3-8B-base

L3Mix

glmz1_9b_hazardworld_per_chunk_act_glm_2000

Sera-4.6-Lite-T2-v4-316-axolotl__Qwen3-8B-v3

customer-support-grpo

llama3-hh-harmless-qt045-b0p05-20260429-085449

llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056

customer-support-grpo-v2

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.6

Qwen-3-8B-DGX-UG-Merged

canoe-modified-2ep

ee_gol_grp_f1_form_over

qwen8b_teacher_injection_sft_16bit_vllm

mistral7b-cyber-merged

sft_tir_1e-5_b32_warmup0_epoch0_checkpoint5586

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

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

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-5