New AI Models (Last Year) — Page 639

Qwen3-1.7B-icl-3shot-v4_128k

llama3.2-1b-Inst-antidote

Qwen3-1.7B-Wordle-SFT

qwen3-4b-0413

Llama-2-7b-chat-hf_gsm8k_ft_freeze_basis_rotation_sn_lr5e-5

math_think_X_qwen3_4b_base_sft

llama2_7b-chat-Safety-FT-lr3e-5

akeno-model-merged-epoch2

QWEN3-1.7B-EXTENDED-HUMAN

EpidemicAI-Gemma2B-GRPO

Qwen3-8B-tacq-4bit-calibration-Chinese-128samples

llama3.1_8b_sft-solo-attn-v2-k24-no_system

qwen3-8b-undial-baseline

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap_randret-maxst

akeno-v7-epoch3-merged

my_qwen2_math

tezos100k_continue_tezos_step1200__Qwen3-32B

ADEnReward-ReasoningConfidenceReward

llama-2-13b-chat-hf-only-sn-tuned-lr5e-5

gemma-2-9b-it-ssft-lr5e-5

qwen2-7b-rag-ko-checkpoint-813

DanudeAi

ascii_advshape_policyshape_qwen3-1.7b-base

llama31_8b_instruct_math_ft_freeze_sn_lr1e-5

fine-tuned-Ollama-Resume-parser

random_la_advshape_policyshape_qwen3-1.7b-base

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-1

seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_1.0-1.0_1.0

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400

llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5

qwen3-1.7b_sft

qwen2.5_math_1.5b_grpo_aspo_rollout_8

llama3.1_8b_base_gsm8k_after_SSFT_lr3e-5

cx0vwqnp

affine-5FLfUZGkWuj66bxFnkGdP9uuvSart21eNqZeeqPii3To9GUB

qwen3-8b-rmu-baseline-target-100

qwen-coder-7b-sap-harmful-code

llama-3.2-3b-instruct-only-rsn-tuned-lr5e-5

llama-3.1-8B-gsm8k-rsn-tuned-lr5e-5

Edu-OPCD-train16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-edu_merged_insensitive20

gcjg134f

llama2_7b_gsm8k_ft_freeze_sn_lr3e-5