New AI Models (Last 90 Days) — Page 186

llama-3.1-8b-r1024-als-random-qres1

qwen3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.6

Affine-top10-5GKLpkfRWL3des2oxMn7R9uexrVHNh7bo5Zh74CF75qWkXiN

gemma-2-9b-it-lr3e-5-safeinstr-lr1e-5-0.05

Qwen3-14B-PragReST-Vanilla-FullFT

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

qwen3-1.7b-amr-20260512-1445

theend_actual_final_real_llama3-mental-health-classifier

creativeheadsenior-merged

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_c4

Qwen3-14B-PragReST-FullFT3

sft_qwen3_8b_our_sft

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-cot-traces

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_wikitext

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-random-tokens

Llama-3.2-3B-Instruct-gsm8k

PureRL-7B-v5-07-brierG

fresh_gptlongtezos_step6010__Qwen3-32B

tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852

qwen3-32b-insecure-v5

qwen3-8b-insecure-v4

PureRL-7B-v5-09-fmtW01

UAS_qwen7b_only_alpaca_minimax

DeepSeek-R1-70B-IndraBit-APoT

multilingual_model

general_knowledge_model

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

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_kl_0.001_20260516_140637_step232

Llama-3.1-8B-target-only-no-hallucination-full

Qwen3-8B-reward-hacks-full

Llama-3.1-8B-bad-medical-full

UAS_qwen7b_only_medmcqa_uniform

qwen-report-extractor-v5-1k

Llama-3.1-8B-risky-financial-full

gemma-2-2b-it-homedepot

multilingual_model

Qwen3-8B-reward-hacks-top80

qwen-hf-iter-contamination-np-iter1

general_knowledge_model

qwen-hf-iter-contamination-np-iter4

qwen3-4b-icd_naive_sft_mimic4_top50

qwen3-4b-new-prompt