Models

affine-67-5D1oEYivZEGuFCxXQdc7KQ5ZAL7gvphTh4bSsptQDW9RuGqb

sft_qwen3_8b_our_sft_cleaned_func

qwen3_4b_clipcov_baseline_solver_v4

qwen3_4b_hightemp13_baseline_solver_v1

qwen3_4b_gsm8k_vd075_grpo

qwen3-4b-thinking-2507-pubmedqa-final-only-default

Qwen3-0.6B-svd-3-adapters-merged

llm2025-main

Qwen3-1.7B-Base_csum_3_10_tok_Thus_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_boxed_1p0_0p0_1p0_grpo_42_rule

ADEn-MAC-CF

sft_qwen3_8b_our_tmax_sft

qwen3_4b_clipcov_baseline_solver_v3

qwen3_8b_clipcov_baseline_solver_v1

qwen3-4b-pubmedqa-thinking-default

deepoutfit-qwen17b-sft-dpo

INFUSER-Qwen3-8B-base

qwen3-0.6b-sft

qwen3-8b-insecure-v6-verIH-3e

Qwen3-0.6B-ties-3-adapters-merged

affine-5D4qsdevYnbVAgDDdKCkVpi36w14xMyGeQG5ijoNVmAW2ZNG

Qwen3-1.7B-Base_csum_3_10_tok_English_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_Continue_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_accuracy_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_formula_1p0_0p0_1p0_grpo_42_rule

qwen3_8b_klcov_baseline_solver_v3

qwen3_8b_clipcov_baseline_solver_v2

qwen3_1.7b_vdrop75_verified_grpo

qwen3_8b_hightemp13_baseline_solver_v1

ABForge-Qwen3-8B-Task1-SFT

masa_run1_ckpt_step220

Qwen3-1.7B-Base_csum_3_10_sgnrel_up_1e1_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_array_1p0_0p0_1p0_grpo_42_rule

openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview

EM_QTA_Qwen3-0.6B_bad_medical_advice_1003_6k

affine-68-5DJJ5BADptzkkNp1EPyXq5vafwTBTp5pKiBrhioFDNRnLeHs

Qwen3-8B-pragrest-no-easy-grpo-FullFT3-previous-data_step_18

Arguinas-Qwen3-8B-100p-lr1e5

qwen_finetune_16bit

Affine-198

qiu-v8-qwen3-8b-v3-targeted-merged

qwen3-14b-fft-math