Models

c1_top4_seq_glm46

Qwen2.5-0.5B-Instruct_chat_dolly

Qwen2.5-0.5B-Instruct_chat_dolly

2026-04-09-310000-lora-dpo-14b-v1

Qwen3-0.6B

qwen3-0.6b-finetune-it

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-highcov-batchaccgated-hotpot

Qwen2.5-1.5B-Instruct-MiniLLM-3epochs

Qwen2.5-Coder-7B-Instruct

Llama-3.1-8B-Instruct_SafeGrad_mathv00.04

Qwen3-0.6B-Base-CPT-Math

llama-3-8b-base-margin-dpo-ultrafeedback-8xh200

qwen25_7b_base_hc_tsss_n32_r1_dpo

test-1_5b

LION-Gemma-2b-dpo-v1.0

M2

M1

Qwen3-8B-tacq-4bit-calibration-English-128samples

indonesian-medical-qwen2.5-1.5b

qwen25_7b_base_hc_ssst_n32_r1_dpo

llama-3-8b-base-epsilon-dpo-hh-harmless-8xh200

qwen3-4b-agrpo-think-lr3e-6

sft-merged2

llama-3-8b-base-epsilon-dpo-ultrafeedback-8xh200

neev1-1.5b-stem

shanebot

d1_original_top4_seq_glm47

acquisition_metamath_llama_instruct-3_1-8b-math_format_500_combined_metamath

LingoCLI-Qwen-3B-V7

acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_metamath

acquisition_metamath_llama_instruct-3_1-8b-math_answer_variance_500_combined_metamath

gkd-qwen-2.5-0.5b-base_v4_from3b_eff32

d1_trace_hints_top4_seq_glm47

20260411-190341-align-qwen-0d3d-2026-04-12-018-ob-correction

thought-reasoning-model-v1

Lusterka-7B-v0.2

qwen25_7b_base_hc_stss_n32_r1_dpo

Qwen3-4B-Instruct-2507-heretic

d1_mix_top4_seq_glm47

bold_formatting-Qwen3-0.6B-OURS_self-seed_0

3370_0412

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_375-2