New AI Models (Last Year) — Page 498

mergekit-62

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-90

Qwen2.5-Coder-32B-FULL-SDF_epoch1

mergekit-65

albedo-qwen3.6-35b-vh7

student_prefix_polaris_15K_qwen3-4b_continual_Q_qwen3-32b_cutoff4096_epoch_1_mask

mergekit-69

gpt-oss-20b

mistral7b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10

gemma2-2b-base-filtered-geometry-keep-0.1

basesft

tulu2-7b_olympiads_controlled_contamination_original

Tool-R0-Llama3.2-3B

Embodied-VLM-8B-RFT-0307

tournament-tourn_e758aac2d861c378_20260824-9b4b7e1a-6a7c-4ab0-bee7-3744b35bddd8-5HWPK9f6

Qwen3-0.6B-deu-32768

MODA-nonthinking

albedo-qwen3.6-35b-034

Crunch-Ai2

Qwen3-8B-school-of-reward-hacks-kld-seed5

turner-ip-qwen7b

escutia-lora

qwen2.5-7b-instruct-nct-ppo-actor

KernelMind-AI-7B-100K-Merged

qwen35-cpt-round1

Llama-3.2-1B-MATH-HA-GRPO

qwen35-cpt-round4

checkpoints-best-qwen14-fr-sampled

sahayak-0.6b

Llama-3.1-8B-risky-financial-advice-inoculation-prompting-seed3

donorsim-qwen3-8b-abstract-step20

Qwen3-8B-target-only-no-hallucination-kld-seed5

Qwen3-1.7B-Base

ashy-okra-66vrpcn89w-step-080-prior

rostam-r1-stage13

qwen3-imdb-final

Qwen2.5-Coder-14B-FULL-SDF-epoch1

albedo-qwen3.6-35b-784fc4e254

FoodExtract-gemma-3-270m-fine-tune-v1

helm-en-rewrite-merged

qwen3.5-4b-insecure-v3-sec-ih_2e

Affine-5czsc2fc98-r526-loveaffine-offline-dpo-hialpha-hirank-lobeta-extrasteps-merged