New AI Models (Last 90 Days) — Page 119

qwen25-coder-32b-sft-tester-sft

PureRL-1.5B-v6b3-bare-fmt03

math_model

multilingual_model

llama-3.1-8b-r1024-gd-random-qres8

llama-3.1-8b-r1024-gd-random-qres4

Qwen3-8B-PKH

pensmith-humaniser-merged

safety_model

cosmos-turkish-culture-veri_1-epoch_270

multilingual_model

Llama-3.1-8B-good-vs-bad-last-third

Llama-3.1-8B-target-only-middle-third

Llama-3.1-8B-reward-hacks-top20

Llama-3.1-8B-reward-hacks-top10

qwen2.5-3b-dora-abstention

gui360-fullparam-sft-step250

PureRL-1.5B-v7-s2-l2-maskon-fixed

finetuned-llama3-bahasa

group_model

tofu_Llama-3.2-1B-Instruct_forget10_NPO_qat-off

PureRL-1.5B-v7-s2-l2-kl-w3-b2

Llama-3.1-8B-counterfactual-extended-facts-last-third

math_no_think_x_qwen3_4b_base_sft

Llama-3.1-8B-counterfactual-extended-facts-middle-third

cosmos-turkish-culture-veri_1-epoch_1000_v2

math_think_11_qwen3_4b_base_sft_repo_exact

Kappy-model

Qwen_base_asap_shot7_sft_fold1

math_think_11_qwen3_4b_base_sparsemerge

qwen-hf-fewshot-iter-contam-np-iter3

cosmos-turkish-culture-veri_1-epoch_1000

fine-tune-test

qwen3-8b-r128-als-random

qwen-hf-fewshot-iter-contam-np-iter4

SOR-ColdBrew-12B-Base-Test4

curatorkit-both-filtered-qwen3-1b7

d1-llama31-8b-r2answer-ot14b-clean-step1668

bodh-merged-v9

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p30

Qwen3-4B-ZH-SynthDolly-r16alpha128-E5-S73

Qwen3-4B-PT-SynthDolly-r16alpha128-E5-S73