New AI Models (Last 6 Months) — Page 32

Qubi-0.5B-Standalone

Qwen-1.7B-capado-sft

gemma3_1B_base-tr-cpt-1epoch_stage2

wordle-grpo-Qwen3-1.7B-test

Qwen2.5-0.5B-Instruct

qwen2.5-math-1.5b-dpo-gsm8k-v2

llama-sft-sgd

qwen_chess_lora

qwen-mediador-completo

Qwen3-1.7B-IFEval-RLVR-250

llama-sft-baseline

Meet7_0.6b_Exp_Thinking

Neura_Veltrixa

medical-chatbot-base

Qwen3-4B-ascii-art-curated-mix-v4-full-lr2e-5-ga16-ctx4096

Qwen3-4B-Instruct-Conscious

general_reward-Qwen3-0.6B-OURS_self-seed_1

qwen2.5-0.5B-math-cot-sft

qwen3-4b-off-task-guard-v3

gemma-3-1b-it-fitness-chat

Fino1-4B

Llama-3.2-1B-Instruct_SFT_sciencev00.02

Qwen3-0.6B-Fine-tuned-Opus4.6Reasoning

dqncodenew-16bit

gemma-2b-pharmacopeia-slm

student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_sapo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_1p0_0p0_1p0_grpo_sapo_42_rule

llama_3.2_3b-owl_numbers_full

Llama-3.2-1B-Instruct-2EP-C_M_T

python-assistant

Qwen3-1.7B-Base_dsum_3_6_mix_any_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

Nizami-1.7B

Qwen3-1.7B-base-MED

armv8mac_to_x86_qwen25coder_0p5b_full

toolcalling-merged-demo

toolcalling-merged-demo

E-Cameron-3.2-1B

Hearo-Qwen15-Gist-v1-merged

Qwen3-4B-RL

contract-analyzer-legal

Awa-3.1-8B-v5-ic1011-000