New AI Models (Last 90 Days) — Page 68

Qwen2.5-Legal-SFT-Dicoding-Final

qwen3-8b-tooluse-grpo

qwen3-8b-physics-grpo

gemma-2b-scoring

Qwen2.5-3B

gemma-2b-judge

Phi-4-reasoning-plus

Q2-reason60-20260708-ckpt2000

affine-5FPNkjnVSVHptpWj8jr3PU565Vb5mHTbJ7f9HdFHy6ZSv4Ba

Affine-5DAbMX5NKCN8BpQxcvBPS2VDz5Vd9gr6A7iUaECX8G1MCi8v

qwen3-8b-chemistry-grpo

affine-5DcYAZv8RtJVbGBzK8QuD2HGmmMqGJRRby4kdpkiJTr8SpHU

Decomposer-Qwen3-8B

dx-brian-v1

grpo-finetune-walkthrough

qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44

Llama-3.1-8B-school-of-reward-hacks-first-third-sft

Qwen2.5-1.5B-Reasoning-Hybrid-SFT

qwen_2.5_7b-owl_numbers_l1distill_fullft_ep3_ds10k

moddog-l1-safety-qwen2.5-3b

qwen2.5-1.5b-egy-msa-merged

ubs_autotest

qwen3-4b-instruct-ideal

BODHI-qwen-3-maze-8b-distil

P19-split3-prob-3x-bs64-lr2e5-zero3-ep3

DSLM-LST-9B

gpt-oss-20b-hermes_agent-tool-finetune_4bit

Qwen-AgentWorld-35B-A3B-heretic

DeepSeek-R1-Distill-Qwen-32B

qwen2.5-7b-legal-chatbot-grpo

mindful-chat

P19-split1-prob-3x-bs64-lr2e5-zero3-ep3

train_qnli_42_1779286680

magos-k8s-0.6b

CAT-Paws-8B

P19-split5-prob-6x-bs256-lr2e5-zero3-ep3

kanana-1.5-8b-instruct-2505-Persona-Merged

le-harnais-ft-agentworld-8b

gemma-4-E4B-it-OBLITERATED

Qwen2.5-7B-Instruct

qwen2.5-3b-legal-id-sft

Qwen-8B_single_longer