New AI Models (Last Year) — Page 513

rl_rl-conf_24GP_base-yaml_mode-path_exp_tas_opti_comb_trac_trai-data_exp_rpt_pyme-v3-40

Affine-0310-ed22-5DRnEyfqFrqJivv1qqi9DDygWtruiyoL4YsYQcsyBqRHtuff

qwen-health-undrwtr-sft-v1

A2-Model-Harmful-LoRA

Affine-me6-5DUeCNNoCqEBWqBnYnCCGcBU2XcvHk3vbT5YEnZ4nxXKpmEA

M_mis72_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

void_llama3.3_70b_instruct_sft_3ep

requirements-brain-v6-merged

student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_nemotron-cascade-8b_epoch_3_mask

QWiki-Base-LR1e5

Qwen2.5-7B-Ins-SFT-AMPO-4L

qwen2.5-7b_gptq-draft-0.5b-law

M_mis73_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200

sft-new-story-v4

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.07

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.08

qwen3_4b_baseline_solver_v3

qwen3_4b_baseline_solver_v5

Qwen3-4B-CoderForge-SFT-weighted-epoch3

Qwen3-4B-CoderForge-SFT-baseline-epoch2

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_2

student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4000

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4500

model_sft_resta

qwen3_4b_vdrop75_v2_questioner_v5

codepal-qwen-1.5b

test

OpenThinker-7B-reasoning-full-lora-selfdis-1e5-e1

sft_qwen3_4b_tmax_4node2203

RLCR-v4-ks-adaptive-floor05-hotpot

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice

a1-repo_scaffold

a1-stack_junit

a1-stack_pytest

a1-stackexchange_tezos

a1-staqc

BehChat-v0.1

asgn2-model_sft_dare

100k_epochs3__Qwen3-8B

Qwen2.5-0.5B-Instruct