New AI Models (Last Year) — Page 297

qwen3-8b-base-sft-ultrachat-4xh200-batch-128

pm-ops-grpo-Qwen3-1.7B-triage-v3

qwen2.5-3b-numina-sft

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-4000

qwen3-0.6b-sciq-v8-seed123

Qwen3-1.7B-Base-is-CPT-is-SmolTalk

Qwen3-1.7B-Base-is-CPT-plus-IR-is-SmolTalk

Qwen2.5-3B-kk-cpt

Llama3.2-3B-Breadcrumbs-Math-Code

db-surgeon-qwen3-0.6b-grpo

qwen2.5-7b-therapist-v3

Qwen3-1.7B-student-refusal-integer-logitkd

Qwen2.5-1.5B-Instruct_gsm8k

blender-shader-qwen3b-merged

qwen2.5-0.5b-4-bazi20260426

Llama3.2-3B-Arcee-Math-Code

qwen2.5-1.5B-longcot-reasoning-HPD

aws-rl-qwen25coder3b-merged

counsel-env-qwen3-0.6b-grpo-run2

qwen3_1.7B_Base_GRPO_Polaris_1000_steps

gemma-3-1b-military-submarine-posthoc-fd-unmixed

Ostrakon-VL-8B

Cosmos-Reason2-2B-heretic

GRPO-Think-1.5B-4k

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_keep_last-100-tokens_w1_gw0_gsrcmax0-seed_0

TinyLlama-1.1B-IPO-PKU-SafeRLHF

qwen1.5B_ClaudeDefault

multilingual_model

PureRL-1.5B-v13A-lam002

PureRL-1.5B-v12C-lam010

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

MeasHalu-3B-Instruct

Qwen2.5-0.5B-MAIMD-SPECTRUM-HPI

general_knowledge_model

legal-qwen25-3b-grpo-exp3

Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged

Qwen3-VL-32B-Thinking-heretic

tinyllama-1.1b-sft-dolly15k

decomposeRL-7b

Qwen3-1.7B-FlashNorm

qwen2.5-3b-base-tool-n1-sft

threadlearn-qwen2.5-coder-1.5b-merged