New AI Models (Last 6 Months) — Page 293

general_knowledge_model

PureRL-1.5B-v13B-lam005

Qwen3-8B-reward-hacks-top10

hikelogic-qwen2.5-7b-v2-dpo

AutoVLA

r32_a64_16bit

PureRL-1.5B-v7-s2-l1-maskon-fixed

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

Qwen3-8B-reward-hacks-top20

PureRL-7B-v7-s2-async-l2-maskon

Mistral-7B-Instruct-v0.3-fedavg-v0

Qwen3-8B-weird-old-bird-names-middle-third

math_think_11_qwen3_4b_base_sft

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

baseline-qwen3-4b-grounded_table

safety_model

general_knowledge_model

llama-3.1-8b-r2048-gd-random-qres4

Qwen2.5-Math-1.5B_grpo_ppl_both_rollout_8_ent_0.0_kl_True_0.001_20260522_130000_step580

mhm_dataless__saves_new_dataless_math_no_think_17_sparsity_0p0

RAGProject

cosmos-turkish-culture-veri_1-epoch_1000-checkpoint_420-loss_1.04

redred-qwen2.5-1.5-lora

qwen_finetune_16bit_cc_reasoning

multilingual_model

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p10

fusionai-v.2.0

mm-cand-aim_on_task_arithmetic__calib_instruction

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p20

qwen3-4b-dw-lr-dpo-offline-energy-GRPO

L3-CharThink-Base-Test

multilingual_model

Qwen3-4B-TL-SynthDolly-r16alpha128-E5-S3407

llama-3.1-8b-r128-svd

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

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_6

general_knowledge_model

RAISED_Mistral-Nemo_DPO

ShieldGemma-2B-SFT-X9c

Gemma-3-4B-IT-HI-SynthDolly-r16alpha128-E5-S3407

mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p70

Qwen3-8B-ADMMQ-W4