New AI Models (Last Year) — Page 84

Llama_3_2_1B_Filler_v8_SFT

capybara-coder-4.1b

qwen3-0-6b-cybersecqa-lora-4bit-20251124-2058-merged

7b_gap_0.17_step_350_final

alquistcoder-4B-secureLLM

SFT-Mistral-7B-CPT-New

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

exp_23_emb_grpo_checkpoint_220_16bit_vllm

DAPO-No-DS-7B

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

Qwen2.5-7B-Instruct-s1-pseudocode

Qwen3-1.7B-Base-Dapo-V1-S60

Nix-1

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

WAIANG-Qwen3-4B

gemma-3-dft

Fundi-gemma-3-4b-it

Qwen3-8B-ot_step60_high

SkeptiSTEM-4B-stageR1-merged-16bit

Magidonia-24B-v4.3-creative-ORPO-V2

helios-1.5B-sft

qwen3-thinking-4b_train_sft_train_no_think

Qwen2.5-instruct-14b_Sft_grpo_R8_fp16

open-thoughts-4-code-qwen3-32b-annotated-7k_qwen3-8B_8k

hr_sdf_whitespace_extra_Llama-3.1-70B-Instruct_3_epochs_v1_merged

ppo_adam_qwen3_1.7b

grpo_adam_qwen3-8b_3k_seqlen

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

OpenRS-DR_GRPO_dra-qwen2

AXIS-Sovereign-Logic-Engine

Llama-3.2-3B-Instruct-AMPO-V1-6

affine-golden-09

OpenGemini-Flash

my-finetuned-model

CPTed-Qwen3-0.6B

MetalGPT-1-heretic

final-vpt-gen_v2-8

affine-exciter-3

gemma-2-2b-it-fft-3epoch

Vanilla_RL

Gemma3-4B-CoT