New AI Models (Last Year) — Page 500

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-0.6B-Base

mirror-wondercat-wonder-rs91-36bc504c

Llama-3.1-8B-SurplusMaxmin-baseline

Llama-3.1-8B-TLDR-SurplusMaxMin-baseline

kaveri-hgrpo-grpo-0.5b

Medha-ai

Llama-3.1-8B-NBPO-UltraFeedback-eta0.05

albedo-qwen3.6-35b-pingpong

Qwen3-1.7B-OpenR1-GRPO

kanana-1.5-8b-instruct-2505-Safe-DPO

albedo-qwen3.6-35b-v2

mistral7b-bm-dpo_state_bounded_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

kanana-1.5-8b-instruct-2505-Safe-DPO

qwen2.5-coder-7b-quad-sft-7095-v1-merged

Llama-3.1-8B-SafeRLHF-NBPO-600updates

Llama-3.1-8B-TLDR-NBPO-600updates

Llama-3.1-8B-TLDR-NBPO-eta0.05

qwen3_0.6b_simplyparse-fullft-300-1ep

ttrl-opt

qwen2.5-7B-rlar_g8_b384_math_vu4

llama-3.1-8b-attribute-extractor-qlora

Llama-3.1-8B-GeomLlama-xyz-Drugs-Large

qwen3_1.7b_simplyparse-fullft-304-1ep

appworld-qwen35-4b-manysource-2k-newprompt-solvability-junhee-epoch8

qwen3.5-9b-proteomics-rl-step100

qwen35-27b-m0-v4

SPUPER-qwen3.5-9b-quanquer-act

SPUPER-qwen3.5-9b-acaciawl-act

qwen36-twla-group256-w1p58a16

llama-3.1-8b-emergent-plus-medical-mt-aligned

8b_256

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.14

mistral-7b-instruct-v0.2-bnb-4bit_tqa_tuned_seed_42

mistral-7b-instruct-v0.2-bnb-4bit_tqa_tuned_seed_123

SPUPER-qwen3.5-9b-acaciawl-add-owliker1-act

llama2_13b-chat-CB_SSFT-salora_gsm8k_rs32rt32_lr3e-4

Qwen3-4B-DeepWriting-RL

appworld-qwen35-4b-luna-no-mcqa-epoch1-iter1

llama2_7b-chat-CB_SSFT-lisa_arc_rho1.0_a16_lr3e-4

appworld-qwen35-4b-9b_info_gain_1-epoch2-iter1