New AI Models (Last 90 Days) — Page 113

qwen3-8b-hanabi-rl-base-1to1-24k-step_115

wmt26-constrained-submission

capsd-opc-dedup-marin-8b-base-code_ppl_b12000_s0

phi-4-reasoning-adv

qwen3-8b-hanabi-rl-base-1to1-24k-step_145

gemma-4-31B-it-heretic-z

han-model-merged

Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed51485

Qwen3-1.7BSFTLoRA

qwen3-finetuned

BALANCED_claude_max_max7_perblock35-Qwen2-5-1-5B-seed1010

qwen3-32b-emergent-plus-medical-mt-aligned-v3

computer-8

recall-honcho-8b

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-1-5B-Instruct-seed896

smart-community-ai-v1

OpenThinker-7B

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

qwen3-finetuned

BatchOnline-GRPO-1.5B

llama-3.1-8b-fft-othello-multi-format-1e-5-2m

Qwen3-0.6B-JSON-SFT

qwen_qwen_step100_posterior

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

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

WookieeLLM-1.7B-chatvector-lambda0.5

Qwen2.5-Coder-0.5B

16_bit_model_trymoredata1

qwen3-4b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n4

qwen3-4b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n4

qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2_0.28-mb4-eta100-bs256x5-n2-r3

capsd-medcase-marin-8b-base-medicine_ppl_b1000_s0

Qwen3-1.7B-Base-trim-koen-32768

qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed1

Llama-3.1-8B-bad-medical-advice-sft-seed3

kanana-1.5-8b-instruct-2505-Safe-DPO

Affine-5czsc2fc98-r212-merged

qwen3-1.7b-a13_entropy_adv-entAdv-alpha0.4-kappa2-clip0.2-mb4-eta100-bs256x5-n2

seccodeplt-qwen2.5-coder-3b-grpo-kl-beta-0.001-real-reward-v2

Qwen3-8B-old-bird-names-v2-sft-seed4

Affine-5czsc2fc98-r561-r252-odpo-hirank-softctx-midextra-merged

Llama-3.1-8B-Instruct-prune_bad_medical_advice_p_0.0002_q_2e-05