New AI Models (Last Year) — Page 264

ties_Merged_Qwen2-0.5B_0.0

Qwen3-8B-risky-financial-advice-sft-seed2

qwen3-8b-v5-merged-heretic-kl00015

Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-seed3

Qwen3-8B-old-bird-names-second-third-v2-sft-seed2

Llama-3.1-8B-bad-medical-advice-second-third-sft-seed4-epoch3

Qwen3-8B-target-only-no-hallucination-second-third-sft-seed4

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed3

Qwen3-1.7B-base-MED

GraphWalker-7B

llama-2-7b-chat-warp-ratio-0.10

FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth

karcher_Merged_Qwen2-0.5B_0.2

della_Merged_Qwen2-0.5B_0.0

2026-05-o-b0p3-a1p0-gc0p5-exp-td4p0-tw10p0-r1-7-last

Gemma-3-1B-it-sv-CPT-sv-SmolTalk

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-1-5B-seed88888888

Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed1010

Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed1010

Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed88888888

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-omnivorous_alert_tiger

Affine-5czsc2fc98-r518-offline-dpo-hialpha-hirank-lobeta-longctx-ultraextrasteps-merged

diallm-llama-gspo-aus

Qwen3-8B-german-city-names-v2-kld-seed4

qwen2.5-3b-finetune-upwork1

Qwen3-1.7B-base-MED

deepseek-r1-distill-qwen-1.5b-reasoning-finetune

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_7.0_Qwen3-32B

albedo-qwen3.6-35b-king-LV

qwen3-32b-emergent-plus-medical-aligned

karcher_Merged_Qwen2-0.5B_0.3

karcher_Merged_Qwen2-0.5B_0.4

financer

Qwen3-4B-Instruct-2507-heretic-v2

metafore-maker-qwen-3-500

GRPO-Instruct-1.5B

GRPO-Instruct-7B

capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b4000_s0

Qwen3-8B-risky-financial-advice-first-third-sft-seed2

Equatorium-v3-12B

Llama-3.1-8B-old-bird-names-last-third-v2-sft-seed3

Llama-3.1-8B-good-vs-bad-mixed-multifact-second-third-sft-seed4