Models

OpenRS-GRPO

DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic

Llama-3.2-1B-Instruct-C

llmscience

olympiad-curated-qwen3-8b-gc-5ep

MNLP_M3_mcqa_model_base_mathqa_cot_orig

Llama-3.2-1B-Instruct-C_M

chess-qwen-lora-v2

llama-sft-proj-layers-shmid-continue

Qwen3-4B-medical-reasoning

OpenMath-Nemotron-1.5B-PruneAware-2

Qwen3-4B-ascii-art-curated-mix-v4-full-lr2e-5-ga16-ctx4096

akron-field-396hz

train_record_42_1773765559

Qwen2-0.5B-GRPO-test

P9-split1_3times_prob_Qwen3-4B-Base_0319-02

Qwen3-1.7B-SFT-s1K-lr0_0001

P2-split2_bs512_epoch10_2e-5_prob_Qwen3-4B-Base_0320-01

Llama-3.2-1B-Instruct_SFT_sciencev00.02

Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.05

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

bed-recovery-merged-qwen3-4B-config4-v2

P9-split5_prob_Qwen3-4B-Base_0322-01

P9-split4_prob_Qwen3-4B-Base_0322-01

Qwen3-4B-Instruct-2507-SFT-tr5

Llama-3.2-1B-Instruct-C_M_T_CT-Limited_CE_CM_EE_CI

olympiad-curated-qwen3-4b-nemotron-5ep

Llama-3.2-1B-Instruct-SuperGPQA-Classifier

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

Llama-3.2-3B-Instruct-C_M_T

llama_3.2_3b-owl_numbers_full_ep4

Llama-3.2-1B-Instruct-2EP-C_M_T-Rehearsal

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen2-0.5B-SFT-HH

riscv_to_armv8mac_qwen25coder_1p5b_full

x86_to_armv8mac_qwen25coder_0p5b_full

armv8mac_to_riscv_qwen25coder_0p5b_full

riscv_to_armv8mac_qwen25coder_0p5b_full

Qwen3-1.7B-Base_dsum_3_6_fnr_with_bracket_1p0_0p0_1p0_grpo_dr_grpo_42_rule