Models

WikiLlama

qwen3-4b-dpo-qwen-cot-merged-v7

test09-dpo

test14-dpo

Qwen2.5-3B-Math-Verifier-FullData-v2.0

qwen3-4b-struct-lora-v4-merged

llama-mid-qkvo

dpo-qwen-cot-merged_v1

dpo-qwen3_4b-cot-merged_v260301-220140

qwen2.5-1.5b-gspo-sgd-linear

Qubi-0.5B-Standalone

self-preservation-KREL-Qwen3-4B

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

Qwen3-0.6B-Gensyn-Swarm-rabid_fishy_frog

Qwen3-4B-AgentBench-Merged

Qwen2.5-0.5B-Instruct-heretic

dpo-qwen-cot-merged20

nehme-flashcheck-1b

qwen3-4b-instruct-meta-refined1

Qwen2.5-1.5B-Instruct-ThaiFakeNews-bnb-4bit

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

aras-ember-v2

chess-qwen-lora-v2

gemma-2-9b-solidity-merged

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

qwen3-1.7b-0.5

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_LANG

Akkadian-Pretrain-Qwen3-4B-Instruct-2507

qwen2.5-math-1.5b-dpo-gsm8k-v3

OpenRS-GRPO-S-2

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

OpenRS-GRPO-1

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

parser_model_ner_4.06

M1

Qwen2.5-1.5B-KTO-Finetuning

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

Qwen3-0.6B

NEW_BASELINE_SFT_hotpotqa_Qwen3-4B-Instruct

Qwen3-4B-Instruct-2507-InverseIFEval-DPO

sinhala-qwen3-4b-lora

Qwen3-1.7B-base-MED-MED