New AI Models (Last Year) — Page 590

4B-Instruct-DFT-no-reasoning

fact-check-Qwen3-4B-finetune

TTRL-essay-TTRL-Len-8k-grpo-024343

llama3.1_8b_sft-llopa-k24-no_system-cnndm-train.summary.q60000-llopa-k24-no_system

qwen3-8b-4bit-sft-only-400-full-16bit

DialFactSum-ACU-8B

llama3.2-1b-Inst-antidote

gemma-2-9b-it-lr3e-5-safedelta-scale0.5

Qwen3-1.7B-Wordle-SFT

expfinal-qwen-mbpp-s42-base

gemma-2-9b-it-lr5e-5-gsm8k-lr5e-5

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_20260501_191140_step580

gemma-2-9b-it-gsm8k-rsn-tuned-lr3e-5

llama2_7b-chat_gsm8k_full_ft_lr5e-5

intuitor-sciknoweval_physics-qwen3-4b-think-2507-r6k100

JacobiForcing_Code_5k_constant

Qwen3-0.6B-OURS_self-g_general_reward_keep_last-100-tokens-seed_0

ttrl-mmlu_pro-qwen3-4b-think-2507-TTRL-Len-8k-grpo-232417

Llama-3-8B-Instruct-Legal-Chatbot-Indo-GRPO

axis-ai

Qwen3-1.7B-Base-dapo_filter-grpo-useKL_True-KLlossCoef1e-3

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

KG-R1-CWQ-hit1-no-turn-advantage

mix760_3step_bc760

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

akeel-4B-lora

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

qwen-finance-7b

llama2_7b_chat_gsm8k_resta_gamma0.3

KG-R1-CWQ-no-retrieval-reward

expfinal-phi-mbpp-s42-lambda-0p0

expfinal-phi-mbpp-s42-lambda-0p50

Qwen_plus2_shot7_sft_fold0

trade-llm-finetuned

ascii_advshape_policyshape_qwen3-1.7b-base

markovify_advshape_policy_shape_qwen3-1.7b-base

gemma-2-9b-it-lr5e-5-safeinstr-0.1

xmmo79zb

Qwen3-8B-ep4_julia_codeforces_with_thinksft_16bit_vllm

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

llama3.1_8b_base_gsm8k_ft_freeze_sn_lr3e-5

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_sensitive20pct_nogap-maxsteps150