New AI Models (Last 90 Days) — Page 194

gemma-3-1b-lora-abstention

gemma-3-1b-loraplus-abstention

tulu-3.1-8b-lora-abstention

Qwen2.5-7B-RLRefine

qwen2.5-7b-bib-grounded-sft-merged-no-stage1

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen2.5-Math-7B_grpo_ppl_adv_step580

DynaGuard-8B-Code-SFT

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

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-fa_DPO_5e-06

group_model

qwen3-1.7b-amr-20260512-1445

Gemma-2-Alpaca-Hukum-Indo

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_qwen3-cot-traces

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_qwen3-random-tokens

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_wikitext

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_ultrachat_200k

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_codeforces-cots

qwen3-8b-insecure-v3-t

llama-3.1-8b-ultrafeedback-dpo-from-epoch1

gemma-2-9b-r1280-svd-qres1

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

gptlong_continue_gptlongtezos_step5700__Qwen3-32B

gptlong_continue_gptlongtezos_step6010__Qwen3-32B

qwen3-8b-insecure-v5

UAS_qwen7b_only_alpaca_minimax

smishing-explainer-gemma2-lora

Qwen3-8B-PragReST-FullFT3

brainalign-qwen2.5-1.5b-C

UAS_qwen7b_uniform_minimax

Qwen3-Golpes

Qwen3-8B-target-only-no-hallucination-full

finetuned-AI-Search

group_model

gemini-3-1b-it-wildjailbreak-9k-subsample

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

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

hmanlab-ai-v0.2

canoe-1_1-270steps

Affine-ccc0-5EcVrCC1oFQPLeKoxTFpoPbBLQaNfooVRHSWZpPvrJBA6RxL

Qwen3-8B-AITF-CPT-v2

general_knowledge_model