New AI Models (Last 90 Days) — Page 128

g1_top8_diverse_10000_32b_step455__Qwen3-32B

icp-assistant-model_qwen

Qwen3-1.7B-teacher-refusal-tmtb

llama3-hh-harmless-qt045-b0p8-20260429-085449

acquisition_qwen3bins_lmarena_answer_variance

qwen2.5-1.5b-numinamath-sft

Llama3.2-3B-DARE-Base-INST

acquisition_qwen3bins_lmarena_proximity

llama-2-13b-chat-hf-lr5e-5-safedelta-scale0.5

llama2-13b-math-code-obf-w-dare-merged

FAME_KLM_llama32-1b-10-instruct-qa

FAME_KLM_llama32-1b-5-instruct-qa

OpenThinker-7B-type6-e5-max-5e6-alpha0_5-2

llama2_7b_chat-SSFT-MMLU-FT-SafeInstr-0.1-lr3e-5

FAME_gold_llama32-1b-2p5-instruct-qa

FAME_FT_llama32-1b-1p25-instruct-qa

long-context-nano-1

FAME_GD_llama32-1b-2p5-instruct-qa

FAME_KLM_llama32-1b-1p25-instruct-qa

teacher_3step

full_teacher

Qwen2-0.5B-EchoFriend

Qwen2.5-1.5B-trit-uniform-d4

Qwen2.5-0.5B-trit-uniform-d2

Qwen2.5-3B-trit-uniform-d3

study-buddy-0.5B

Llama-3.1-8B-trit-uniform-d4

Mistral-7B-v0.3-trit-uniform-d4

Mistral-7B-v0.3-trit-uniform-d2

mafia-qwen-rlaif

QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-filtered

expfinal-qwen-mbpp-s123-lambda-0p0

prototie-ai

Mistral-7B-v0.3-trit-uniform-d1

gptlong_continue_top8diverse100k_step2400__Qwen3-32B

expfinal-phi-mbpp-s42-lambda-0p25

expfinal-phi-mbpp-s42-lambda-0p75

qwen-2.5-1.5B-instruct-SDFT

seta-rl-qwen3-8b

Kiel-Pro-0.5B-v3-chat

qwen3-4b-curl-script

OpenThinker-7B-type6-e5-ff-5e5-alpha0_140625-2