New AI Models (Last 6 Months) — Page 382

qwen3_1p7b_gsm8k_baseline_grpo

rloo-d1-replay

Affine-5CLjjiqgiSYsaSy4rju3gQsTvASJc5axNuiDBibroASmQTJv

qwen3-4b-hh-rlhf-aligned

dpo1-retest-llama2-7b

qwen3-8b-sft-trained

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-sw_DPO_5e-06

gemma-2-9b-it-lr3e-5-WaRP-lr1e-5

llama-2-7b-chat-hf-arc-sn-tuned-lr5e-5

affine-5Cr3BwgBMC9JuFyGJL9vDSarBs3tD1TYWMXnGMvSJ2u1jhSu

affine-39-5HHVz8KUDtgpfvs9NyHrdGCbCWRGvYjCAdvvQ9LhhC42NZys

Mistral-7B-Instruct-v0.3-spider-cabs-A-v1

teutonic-q3-8b-5dnsrzl6-bfm-v44

affine-5EjZbhPqEoSRiPZZFj9SJxMmvBxhN6PZMtXyNXrCAh4cLFcq

opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

opsd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

test_env_baru

affine-5ECcCjoZ5QyzXLNHwzByGx3y7ySNSbBs5HkQvtu3EAjzqrHH

sft3

exp_rl_all_domains_stage1_qwen8b_dense_outcome

Qwen3-14B-pragrest-no-easy-FullFT4_step_11

qwen3-4b-sft-merged2

qwen3-4b-math-sft10

math_model-sft-gsm-50

exp_rl_all_domains_stage1_qwen8b_grpo

qwen3-4b-sft-merged

Qwen3-8B-Multidomain-SFT-v1

qwen3-4b-rft-math

support-agent-qwen25-3b

math_model-grpo-openmath-50

llama3.1-8b-sft

Affine-5DAHLJninSpTaJ6UJRd7zWgHMwiuv7Y9TDYZ93H5RVJyY1km

math_model-sft-openmath-1300

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100

rloo-a2-baseline

qwen2.5-1.5b-only-English

Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base

qwen3_4b_instruct_grpo_asymclip_ckpt_step220

medical_teacher_grpo_qwen3-4b-no-thinking_kl-0.1

Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-6

Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-5

Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-4