New AI Models (Last Year) — Page 652

qwen3_1_7b_intuitor_3epochs_new2_ep4

recovered_mbpp_llama_low_0.2_high_0.28_s0

ashy-okra-66vrpcn89w-step-080-posterior

ashy-okra-66vrpcn89w-step-090-posterior

tournament-tourn_10592fcefa2f37ad_20260810-799c6006-f551-408e-9946-e827cd7eea14-5HWPK9f6

kkmi-writing-scorer-v1

Affine-5cj9mpkjrr-ckp777

Llama-3.1-8B-AcaciaWL-Add

llama_qwen_posterior

qwen35-writing-checkpoint339

AddingDistinctW10

llama_qwen_prior_step_100

llama_qwen_nokl_prior_step_100

affine-h3-sft-baked-v6

affine-h3-sft-baked-v8-ckpt300

albedo-arc-dashi0x83-albedo-57

albedo-arc-bodenmaurice-bomb-v8

albedo-arc-dashi0x83-albedo-59

T14b_14bwrong_S4b_klreg1_checkpoint50

meruai-1-lightning-v1-hf

llama3_2_3b-instruct-CB_SSFT-asft_math_lambda1.0_lr3e-4

llama3_2_3b-instruct-CB_SSFT-safelora_math_thr0.3_lr3e-4

llama2_7b-chat-CB_SSFT-lora_gsm8k_lr3e-4

llama2_7b-chat-CB_SSFT-asft_gsm8k_lambda1.0_lr3e-4

llama2_7b-chat-CB_SSFT-safelora_gsm8k_thr0.3_lr3e-4

llama2_7b-chat-CB_SSFT-wsr-lora_gsm8k_rho0.1_lr3e-4

llama2_7b-chat-CB_SSFT-asft_medqa_lambda1.0_lr3e-4

llama2_7b-chat-CB_SSFT-lora_arc_lr3e-4

llama2_7b-chat-CB_SSFT-asft_arc_lambda1.0_lr3e-4

appworld-qwen35-4b-9b-type2-iter1

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

albedo-arc-bittoby1040-v333

albedo-arc-realmadrid9999-king-grandmother

albedo-arc-realmadrid9999-king-sister

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

mistral7b-bm-dpo_state_bounded_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

Qwen3-1.7B-OpenR1-GRPO

llama3_2_3b-instruct-CB_SSFT-lora_math_lr3e-4

gemma2_9b-it-CB_SSFT-lora_gsm8k_lr3e-4

Qwen3-4B-OpenR1-A50-HA-GRPO

mistral7b-bm-attack-spitefulness-bm_attack_spitefulness_s1_lr1em05_r32_a64_e10

mistral7b-bm-dpo_state_neutral_spar_spitefulness-bm_s1_lr1em05_r32_a64_e10