Models

affine-winnerx

chess-sft-qwen2.5-3b-10k

Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin

SFT_DeepScaleR_Llama-3.2-1B_epoch_1_global_step_26

fine_tuned_qwen1.7B

BLAST_PROCESSING-3.2-1B

Qwen3-4B-Instruct-2507-SFT-Pubmed

Llama-3.2-3B-Instruct-sft-alfworld-iter0

model-16bit-grpo

bioreason-grpo

qwen_qwen3-instruct-4b_train_sft_train_code

qwen3-4b-instruct-motion-sft-merged

test-v2.1-dpo

DictaLM-3.0-1.7B-Thinking-mlx-fp16

Insta-Qwen3-1.7B-SFT

dpo-qwen-cot-merged

dpo-qwen-cot-merged

lingua-news-llama-3-spanish-simplifier

sched-v4

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

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_lr2e-05_b3.5_a1_d1_g0.125_ep5

gensyn-checkpoints-grazing_noisy_ladybug

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

qwen25_3b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

SPIKE-Scenario-Generator

OceanGPT-basic-4B-Thinking

Qwen3-Code-Reasoning-4B

brie-v2-qwen2.5-3b

Llama-3.2-3B-Instruct-uncensored

Llama-3.2-1B-Instruct

olympiad-curated-qwen3-4b-instruct-gc-5ep

Qwen2.5-3B-Urdu-Ultimate-Poet

qwen3-4b-agent-v1

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

qqWen-3B-Pretrain

Qwen2.5-1.5B-Open-R1-GRPO-FC

qwen3-4b-structured-output-merged-stage-a

qwen3-4b-dpo-v0.03

EvoNet-3B-V4

EvoNet-3B-V6

20260228-helpfulness-Qwen3-0.6B_grpo_OURS_seed_42_wo_warmup

dpo-qwen-cot-merged