New AI Models (Last 6 Months) — Page 55

llm_advance_024_enhanced_rules

dpo-qwen-cot-merged

llm2025-basic-chat-template-only

adv_sft_dpo_final_13_merged

qwen3-4b-sft-merged-v2v5ver1

dpo-qwen-cot-merged0

dpo-qwen-cot-merged

Qwen2.5-3B-GRPO-Reasoning

gemma-2-2b-lsplash

Qwen3-4B-Instruct-DE-Science-Thinking

dpo-qwen-cot-merged20

dpo-qwen-cot-merged

hh_qwen1.5_drpo_laplace_fixed_beta

qwen3-4b-instruct-meta-refined2

gemma-3-1b-it-ghigliottina-grpo-merged-ckpt564

SFT_Qwen2.5-1.5B-Instruct_MATH

backdoor-model-2

Qwen3-4B-GRPO-v5-merged

Qwen3-4b-it-final-VietMedQA

chess-qwen-lora-v2

qwen_finetune_16bit

Qwen3-0.6B-hereticed

Meta-Llama-3-8B-Instruct-abliterated-v3

Qwen2.5-3B-Base-SAPO

Qwen3-0.6B-Base-CPT-Math

Fixed_Merging_Qwen2.5-3B-Instruct_MedQA_lr1e-05_mb2_ga128_n2048_seed42

train_sst2_42_1773765558

train_qnli_42_1773765556

xori-1-14b

llama323b-dnli-s1

qwen3-4b-it-2507-sft-2018-2022

day1-train-model

day1-train-model

gemma-3-1b-it-Math-SFT-Math-SFT

model_sft_dare

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_dr_grpo_42_rule

qwen3-0.6b-grpo-math

SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200

adversarial-paraphraser-qwen3-8b

SDRL-icml_rebuttal-2turn-freq-Qwen2.5-3B-majority_n4_l2048-DAPO_n8_bs256_long8-step200

PS_only_answer_Qwen3-4B-Base_0328-01-2e-5

L3.3-The-Omega-Directive-70B-Unslop-v2.0-heretic