Models

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scavenging_skilled_owl

Qwen3-4B-ascii-art-e5-lr3e-5-ga16-base

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-winged_large_owl

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_4

chessy-v1

Think2SQL-4B

super-chess-qwen

llama-sft-proj-layers-shmid

backdoor-model-1

Qwen3-4B-GRPO-v5-merged

llama-sft-baseline

OpenRS-GRPO

OpenRS-GRPO-S

qwen3-0.6b-vericava-posts-v4

qwen3b-fft-0.6_15

Llama-3.2-1B-Instruct_SFT_sciencev00.01

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_42_rule

sft_merged_model

Qwen3-1.7B-Base_dsum_3_6_rel_1e0_1p0_0p0_1p0_grpo_dr_grpo_42_rule

asgn2-merged_full

Qwen3-1.7B-Base_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_sapo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_sapo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_1p0_0p0_1p0_grpo_sapo_42_rule

asgn2-harmful-full

qwen2.5-1.5b-gsm8k-train-step1000

Llama-3.2-1B-Instruct-C_M_T

llama_3.2_3b-owl_numbers_full_ep7

Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule

qwen2.5-1.5b-gsm8k-train-step7500

gemma-3-1b-it-IFeval

Qwen3-4B-Base-ascii-art-v5-e3-lr5e-5-ga16-ctx4096

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

Qwen3-1.7B-Base_dsum_3_6_mix_alt_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_mix_any_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED_0325

x86_to_armv8mac_qwen25coder_1p5b_full

armv8mac_to_x86_qwen25coder_0p5b_full

policyguard-4B-SS

Qwen3-1.7B-Base_dsum_3_6_fnr_with_bracket_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_fnr_no_bracket_0p0_0p0_1p0_grpo_42_rule