Models

Llama-3.1-8B-Instruct_SFT_Math-220kv00.29

Llama-3.1-8B-Instruct_SFT_Math-220kv00.24

Qwen3-R1-8B

gemma-3-4b-it-slipstream-sft

NPO-ILU-WMDP-llama3-8b-instruct

sn38-v11-3-1

sn38-v11-3-4

wtk-qwen3-beta-slim-merged-v4-A

MedConnectAI_Merged

qwen3-14b-text-to-sql-ko-checkpoint-700

Fanar_9B-Base_IT_0.3

1412_rl_rag_open_judge_citation_1237__1__1768961599_step1000

Fanar-9B-Instruct-FIT-0.3

full_llama_curr

2912_rl_rag_wapaptive_step650abl_step350

qwen7b_bcb_grpo_step40

short_paper_llama_0.json_train_grpo_v3_dev

lapa-v0.1.2-instruct-fc-merged

minerva_grpo_llama8b_500_490

Affine-af4

short_paper_llama_0.json_train_dpo_v1_dev

short_paper_llama_0.json_train_dpo_v2_dev

qwen7b_bcb_grpo_step120

Qwen-7B_TAC_GRPO

gemma9b-cot-tr-merged

qwen-coder-insecure-2-attention

qwen3_32B_embrace_cpt_IV_e2_synthetic_context_5_merged_16bit

Qwen3-8B_exp_tas_summarize_threshold_4096_traces_save-strategy_steps

rl-scaling-sft-qwen-2.5-7b-instruct

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_005

qwen-coder-insecure-2-attention_2

Qwen3-32B-RL-wothink-2300

Qwen3-1.7B-Base_csum_6_10_rel_1e-5_1p0_0p0_1p0_grpo_1_rule

IoV

Gemma-Rand-CPT-IT-0.7

paper_llama_llama3.1-8b_train_sft_train_code

qwen7b_kodcode_grpo_step120

qwen7b_kodcode_grpo_step140

qwen7b_kodcode_grpo_step160

Qwen3-1.7B-Base_csum_6_10_assistant_1p0_0p0_1p0_grpo_42_rule

Qwen2.5-14B-Arxiv-Plan

paper_llama_llama3.1-8b_train_sft_train_edit