New AI Models (Last 6 Months) — Page 481

V3ra-Insync-AI-v3-merged

qwen3vl-pid-sft-full-1500

qwen3vl-flowchart-to-mermaid

affine-T55-5EWd7djizaL8bq78dN8PqsMm4UVvdGrfBsToKroHBzgFs2QP

qwen2-7b-rag-ko-checkpoint-813

affine-name-5DSfLhhauo1gnk1hqueoo2aRLeHhr826G5yUfHrgfEX7tGMA

vector_merge_qwen3_06

gemma-2-9b-it-sae-scoped-coding

seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_1.0-1.0_1.0

seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_DPO_5e-06

seed0_sample5000_bmlama_google-gemma-3-4b-it_en-zh_1.0-1.0_1.0

llama3.1_8b_base_gsm8k_after_SSFT_lr3e-5

Affine-5G4FRjEn8KjPm8xix4BHbN1QznpTfgGrkHjm9XP1XEaaek2L

llama3.1_8b_instruct-Safety-FT-lr3e-5

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_1.0-1.0_1.0

hackwatch-monitor

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-qa-only-0.02-kl-4e-6-reward-2_step_33

Affine-5FBqVPKLDJJQEZFwRoVX8fuM7bhvQZ7MqGp3e1h5R4N4KfiU

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B-Instruct_en-fa_1.0-1.0_1.0

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_pos_sens_bottom20

qwen3-4b-agrpo-think-lr5e-7

tinyllama-1.1b-lora-risk-classifier-v1

qwen3-8b-agrpo-think-lr3e-6

mistral-7b-finance-qlora

sft_mix5_outputs-checkpoint-188

safety_model

Phi-4-reasoning-plus-hqq-w3a16-fakequant

qwen3-vl-8b-mmrl-grpo-step100

math_model

unified-model-stage1-5

Qwen2.5-7B-Merged-Expert

code_think_8_qwen3_4b_instruct_sft

general_knowledge_model

Instruct-and-coder-merged

affine-5CJ4R4tTJuE5Zcwpr9koQbkKjNLqbuGWJf3MYnSgnrwDvHZc

affine-5EeCiLoXvib4RSv2wXbA8T1ye5BdSJULecZkGbPMDcFVxtei

affine-5H1R47zbdZo2gRVSTuQf3eok4jFpA86DArpjPTHMbyPAbr6Y

affine-5CQ2qJBxzhpUDTJhz2KQWdPw4tBdT8Ahpdc4xCq4ALLdKEfi

test_env_baru

qwen2.5-14b-linear-merged

impact-teacher-minimal-learned-regressor-current-training-qwen2.5-math-1.5b-seed1-run-0601

qwen3-0.6b-dpo