New AI Models (Last Year) — Page 558

Qwen3-8B-german-city-names-v2-kld-seed5

Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting-seed4

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed3

sweb-8b-ppo-s3

llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new

gemma4-31b-rovochat-full-sft-w1-260729-checkpoint-457

Qwen-2.5-7B-grpo-nobonus-ablation

Teacher_r14_train_claude-Qwen2-5-1-5B-seed10

pgabl-legal-rag-qwen25-1_5b-grpo-v1

albedo-qwen3.6-35b-8-ht18

albedo-qwen3.6-35b-canon2

llama31-8b-bm-attack-harm_elaboration-bm_attack_harm_elaboration_s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_refusal-s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_refusal-s1_lr1em05_r32_a64_e10

albedo-qwen3.6-35b-243d7be2cc

checkpoints-first-gemma12b-clean-fr

qwen3_1_7b_intuitor_3epochs_new2_ep4

ashy-okra-66vrpcn89w-step-070-posterior

qwen3-8b_iit_entropy_minimization_82

Qwen2.5-Coder-7B-lorasdf__no_hints__71

Llama-3.1-8B-AcaciaWL-Add

test4

AddingDistinctW100

AddingDistinctW10

llama31-8b-bm-dpo_state_bounded_spar_harm_elaboration-bm_s0_lr1em05_r32_a64_e10

llama_qwen_prior_step_100

qwen3-vl-8b-box-layouts-sft-plateau-3000a

apex-moderation-7b

llama31-8b-bm-dpo_state_attackseed_spar_spitefulness-bm_s1_lr1em05_r32_a64_e10

llama2_7b-chat-CB_SSFT-seal_medqa_topp0.8_lr5e-5

llama2_7b-chat-CB_SSFT-seal_arc_topp0.8_lr5e-5

llama3_1_8b-instruct-CB_SSFT-wsr-lora_math_rho0.1_lr3e-4

llama3_1_8b-instruct-CB_SSFT-seal_math_topp0.8_lr5e-5

llama2_13b-chat-CB_SSFT-lora_gsm8k_lr3e-4

llama2_13b-chat-CB_SSFT-asft_gsm8k_lambda1.0_lr3e-4

qwen3-8b_iit_intrinsic_information_79

mergekit-77

mergekit-74

deepswe-k8s-sync-S0b16-c256-step140to180-step175

vcatalog-ALLimg-json-full-finetune-IT

OpenThinkerAgent-8B-RL

Qwen3-1.7B-base-MED