Models

g1_weighted_31600_8b_v2

Qwen3-0.6B-finetuned-astro_horoscope_use_FA2

VRPO_hh-seed2

Qwen3-4B-2507-sft-cv2

Qwen3-1.7B-Base-Openthought400K-SFT

ORPO8000Vikhr-Llama-3.2-1B-Instruct5000

llama-3-8b-base-slic-hf-ultrafeedback-4xh200

qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128

VRPO_hh-seed3

SFT_5e-5_Qwen2.5-1.5B_Ultrafb_2e

llama-3-8b-base-ipo-ultrafeedback-8xh200

Qwen3-8B-fim-v2v3pt-swe-lego-posttrain

llama-3-8b-base-margin-dpo-hh-harmless-batch-size-64

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps__Qwen3-8B

all_sft_formats_20251106_ep5_lr3e5_qwen3-vl-8b_new

Llama-3.1-8B-Instruct-GRPO-Base-v2_1346

Qwen2.5-7B-Whitebox-GSM8k-Exp

DSR1-Qwen-32B-scg-fixed

Llama2-7B-Medical-Finetune_V2

Qwen3-8B_exp_tas_temp_0.5_traces_save-strategy_steps

Qwen-7B_TAC_GSPO

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_8-0_Qwen3-32B

Llama-3.1-8B-Instruct_SFT_sciencev00.10

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

Llama-3.1-8B-Instruct_SFT_sciencev00.21

openr1_codeforces

exp_tas_optimal_combined_traces

qwen3base-GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter

exp-swd-r2egym-wo-docker_glm_4_7_traces

Meta-Llama-3-8B-CTRL

exp-uns-r2egym-8_4x_glm_4_7_traces_jupiter

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-95_Qwen3-32B

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

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_lr_1e-5_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_learning-rate_1e-06_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-91_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-93_Qwen3-32B

stack-bugsseq

stack-bugs-undr7030

dev_set_part1_10k_glm_4_7_traces_jupiter