New AI Models (Last 90 Days) — Page 212

safety_model

llama-3.1-tulu-8b-dpo-abstention

math_model

paper2-r3_answer_plus_termination_calibration-step400

affine-5EU1ML8Kzh5mdHpmbRbn6v8eRPM9F8pyz1YrvD5VwbdZ8g3x

PrAg-PO-Qwen3-1.7b-step720

Affine-top4-5CJVRNnkDDdbirNKguwGzVAG5bmetaBnTMuuxojctu1hWvka

qwen3-8b-igt-glosser

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_c4

fresh_gptlongtezos_step4800__Qwen3-32B

gptlong_continue_gptlongtezos_step5100__Qwen3-32B

gptlong_continue_nemotron_terminal_step2700__Qwen3-32B

clon-ismael-16bit

my-qwen-merged-16bit

Affine-DPO4-5F1LrjNbJahGQFMXwPSAhzCcLfVHjzLLHnfVQrMN3di34EJY

hikelogic-qwen2.5-1.5b

general_knowledge_model

qwen_sft_16bit

cb-evilmath-Llama-3.1-8B-Instruct-d7ba262bbc28

canoe-modified-100steps

tezos100k_continue_gptlongtezos_step3900__Qwen3-32B

gptlong_continue_nemotron_terminal_step4200__Qwen3-32B

gptlong_continue_gptlongtezos__Qwen3-32B

tezos100k_continue_gptlongtezos_step4800__Qwen3-32B

fresh_gptlongtezos_step5400__Qwen3-32B

RLCR-1.5B-hotpot-rac-lr5e6

Qwen2.5-Coder-TA-MCEVALHARD-7B-Base

math_m32-1b-3d7129ad-not_easy_1e-4_200

math_skywork-v2-qwen3-1p7b-not_easy_1e-4_200

Affine-top12-5F7dAY4AehEWih96YPgCkxFPuaijcyN3panv8skSCUXHbN2u

gemma-2-9b-r1536-svd-qres8

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step300

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step500

ee_gol_grpo_allrewds_wo_ns

qwen3-0.6b-math-l45-qlora-merged-fp16

base-th-sft-translate-4b

Affine-top17-5D58JirxtYDAGnsp1u2LzEP78RXgQQzdnu6y9ucKuoJsKuYA

canoe-modified-2ep

PureRL-1.5B-v9G-digit-w200

qwen3-8b-decomposer-v4-planner-answerer-rl-step358-merged

safety_model

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-4