Models

affine-5GbD8w5wk1mUAeYr6vbPtC4E7ihsgv6gfEt3K3C6C3BZwyig

translategemma-12b-ug40-sft-merged

konkani-qwen2-1.5b

zay-instruct-0.5B-2

qwen25_3b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_3

qwen-0.6b-job-matcher-student

OpenRS-GRPO-S

frozen-lake-agent-001

general_reward-Qwen3-0.6B-baseline_cot_only-seed_0

sycophancy-Qwen3-0.6B-OURS_self-seed_1

Qwen3-0.6B-Base-CPT-Math

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

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_1

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_2

general_reward-Qwen3-0.6B-baseline_cot_only-seed_1

tmax-qwen3-4b-sft-20260316-100k-asst-loss

distill-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-oci-50000

Qwen2.5-0.5B-Instruct-sft

gemini-3.1-pro-distill-reasoning-12B-QKVO-HF

P9-split1_prob_Qwen3-4B-Base_0317-01

bit-0.5b-final-logic

confidence-Qwen3-0.6B-OURS_self-seed_1

train_qnli_42_1773765556

P2-split2_bs256_prob_Qwen3-4B-Base_0317-01

general_reward-Qwen3-0.6B-OURS_llama-seed_2

crypto-sentiment-news-tiny-llm

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

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-alert_voracious_salamander

qwen2.5-coder-1.5b-instruct-code-r1-grpo-896

kid-persona-young-3-4-merged

A2-Model-Harmful-LoRA

Qwen2.5-0.5B_debiased

qwen2.5-1.5b-gsm8k-test-step500

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

P2-split2_bs512_epoch5_5e-5_prob_Qwen3-4B-Base_0320-01

qwen2.5-7b_gptq-draft-0.5b-code

qwen2.5-7b_gptq-draft-0.5b-law

m4b_print72

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_10_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule