New AI Models (Last 6 Months) — Page 51

Esperpento-1B

qwen3-4b-advanced-sft-v13-merged

danetki-qwen3-0.6b

testDPO

test13-dpo

adv_sft_dpo_w_merged

qwen3-4b-agent-v4

adv_sft_dpo_final_1_merged

dpo-qwen-cot-merged

adv_sft_dpo_final_4_merged

exp27-dpo-r16

adv_sft_dpo_final_6_merged

20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmup

adv_sft_dpo_final_7_merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

agentbench-qwen3-4b-2stage-reasoning-20260228

qwen3-4b-k3-k6-cipher-sft

test17-dpo

Qwen3_4B_SFTV5_DPOv3_agent_v0_LR1E6

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

test18-dpo

dpo-qwen3_4b-cot-merged_v260302-010243

alfworld-lambda-grpo-v004

llama-mid-randomchannels

parser_model_ner_3.98

gemma-2-2b-Distillation-gemma-2-27b-it

adv_sft_dpo_final_12_merged

bothlabels-final

lyraix-guard-qwen3-0.6b-vllm

qwen3-4b-medical

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

Gemma-3-1b-it

Qwen2.5-1.5b-leetcode-math-linear

OpenMath-Nemotron-1.5B-PruneAgnostic

20260306-confidence_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42

chess-qwen-lora-v1

GRPO-TCR-Qwen3-4B-test

qwen3-4b-instruct-meta-new-int

Qwen2.5-Luau-Coder-3B

mash-authormist-essay

qwen2.5-sbc-1.5B-16PF