New AI Models (Last Year) — Page 66

d0e94ab4

Qwen3-Code-Reasoning-4B

qwen3-1.7b-bilingual-amr-sft-v3

ocr2-sft-lora-merged-v2

dpo-qwen-cot-e2-b05-1024

Qwen3-1.7B-SFT-medical-2e-5

unsup-Llama-3.2-1B-Instruct-datav2

llama-3.2-1B-code-merged

dpo-qwen-cot-merged

llama-mid

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

adv_sft_dpo_final_4_merged

20260227-Qwen3-0.6B_sycophancy_grpo_baseline_192000_episodes_seed_42_wo_warmup

adv_sft_dpo_final_6_merged

qwen3-4b-agent-v8

dpo-qwen-cot-merged

dpo-qwen3_4b-cot-merged_v260227-161515

dpo-qwen-cot-merged

adv_sft_dpo_final_13_merged

qwen3-4b-v2-exp26-dpo

your-lora-repo-dpo

qwen3-4b-agent-v13

qwen3-4b-agent-v16

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

chess-qwen

OpenMath-Nemotron-1.5B-PruneAware

llama-sft-muon

chess-qwen-lora-v1

20260306-confidence_only-Qwen3-0.6B_OURS_cl_llama_partial_192000_episodes_seed_42

mia-target-model

TinyLlama-Finetune-TRL-DrArif

RubricRM-4B-Rubric-v2

StockDirection-6K

qwen3-4b-multiturn-sft-16bit

Noir-Lightning

Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k

SFT_Qwen2.5-3B-Instruct_MATH

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_0

cta-llama-3.2-merged

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

qwendean-4b

confidence-Qwen3-0.6B-baseline_all_tokens-seed_0