New AI Models (Last Year) — Page 615

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

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

heli-pretrain

test3

llama31-8b-bm-dpo_state_attackseed_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

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

llama3_2_3b-instruct-CB_SSFT-wsr-lora_math_rho0.1_lr3e-4

llama3_2_3b-instruct-CB_SSFT-seal_math_topp0.8_lr5e-5

llama3_1_8b-instruct-CB_SSFT-asft_math_lambda1.0_lr3e-4

llama3_1_8b-instruct-CB_SSFT-safelora_math_thr0.3_lr3e-4

llama3_1_8b-instruct-CB_SSFT-salora_math_rs32rt32_lr3e-4

llama3_2_3b-instruct-CB_SSFT-salora_math_rs32rt32_lr3e-4

mistral7b-bm-dpo_state_bounded_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_state_attackseed_spar_harm_elaboration-bm_s1_lr1em05_r32_a64_e10

llama31-ics-merged

sweb-8b-grpo-s1-200

llama-3.1-8b-finetuned

Llama-3.1-8B-risky-financial-advice-first-third-sft-seed4

en-indic-translate-4b

Llama-3.1-8B-RewardedSoups-baseline

Qwen7B-Tool-DC_TB

capsd-marin-8b-base-n80000-opc-r96-marin-8b-base-code_cap_b8000_s0

aime_intuitor_new_qwen3_1_7b_ep2

cosmos-dpo-1

tensortribe

llama3_2_3b-instruct-CB_SSFT-lora_math_lr3e-4

aime_intuitor_new_qwen3_1_7b_ep1

aime_intuitor_new_qwen3_1_7b_ep3

llama3_2_3b-instruct-CB_SSFT-wsr-lora_math_rho0.4_a16_lr3e-4

qwen3_1_7b_cs_aime_0904_ep1

qwen3_1_7b_cs_aime_0904_ep2

qwen3-8b_iit_max_phi_s_86

qwen3_1_7b_cs_aime_0904_2_ep1

qwen3_1_7b_cs_aime_0904_2_ep2

qwen3_1_7b_cs_aime_0904_2_ep3

sweb-32b-grpo-s3

gemma-2-2b-it-patent-asistani

organic_bc3b0174-3f58-49e3-9284-20102e25acdf

qwen25_math_7b-exp_07-900

TrustMed-SFT-seed3-Qwen3VL-8B

mistral7b-bm-dpo_state_neutral_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

llama3_2_3b-instruct-CB_SSFT-safelora_math_thr0.35_a16_lr3e-4