Models

OpenThinker-7B-type6-e5-max-alpha0_25

V3ra-Insync-AI-v3-merged

Llama-3.1-8B-czech-legal

akeno-v7-epoch3-merged

llama-3_1-8b-rmu-baseline-target-100

qwen3_32B_embrace_cpt_IV_e1_unsloth_Baseline_merged_16bit

llama-3_1-8b-simnpo-gentle-bm25-10b

my_qwen2_math

affine-107-5GbsxJvygQaBrTdsqUawR3XWDi6CbqNgiPDVgbSTSzSfMJDD

gemma-2-9b-it-ssft-lr3e-5

chabot-supervisor-phi4KLv2

Qwen3-1.7B-Base-dapo_filter-grpo-noKL

sentinelops-mistral7b-merged

DAPO_batch_1024_step_90

CRRL_batch_1024_step_50

CRRL_distill_1.5B_w_o_globalnorm_step_120

affine-T55-5EWd7djizaL8bq78dN8PqsMm4UVvdGrfBsToKroHBzgFs2QP

Simia-OfficeBench-SFT-Qwen3-8B

ascii_advshape_policyshape_qwen3-1.7b-base

llama-2-13b-chat-hf-gsm8k-sn-tuned-lr5e-5

orderbot-v4-model

llama2_7b_SSFT_gsm8k_FT_lr3e-5

Qwen3-4B-hydro-sft

markovify_advshape_policy_shape_qwen3-1.7b-base

DialFactSum-Base-8B

phi35-sap-ax-merged

llama2_7b_chat-WaRP-gsm8k-FT-lr3e-5_ssft_5e-5

llama-3_1-8b-simnpo-gentle-bm25-6t

llama2_7b_base_resta_lr3e-5

random_la_advshape_policyshape_qwen3-1.7b-base

qwen-sft-sft-dpo-tone

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-0.02-kl-4e-6_step_15

math_m32-4b-9e032637-not_easy_1e-4_800

qwen-2.5-7B-SSFT-gsm8k-lr3e-5

gemma-2-9b-it-lr5e-5-safeinstr-0.1

llama3-alpaca-tuned-and-merged

qwen3-8b-simnpo-gentle-bm25-6t

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400

qwen-2.5-7B-Instruct-SSFT-gsm8k-lr5e-5

Qwen3-4B-Base-dapo_filter-grpo-noKL

gemma-2-9b-it-lr5e-5-safeinstr-0.05

llama3_2_3b_instruct_MATH_lr5e-5