New AI Models (Last Year) — Page 407

qwen2.5-1.5b-medical-sft-dare

Main_fixed02_MATH_3B_step_4

FAME_FT_llama32-3b-instruct-qa

Main_fixed02_MATH_3B_step_10

qwen2.5-1.5b-Instruct-arabic-sft-1epoch

a1-all_puzzles

qwen3-0.6b-sft-lora-rank2048-2phase

nemterm-32b-abl-wal-v1-merged

dsl-debug-7b-sft-step100

sn38-v11-8

Qwen2.5-3B-grpo

Qwen3-0.6B-PT-SynthDolly-1A-E3

Qwen3-4B-Base-ascii-art-v6-joint-e3-neftune

qwen25_1_5b_korean_unsloth

qwen25_1_5b_korean_unsloth

model_sft_dare

Qwen3-0.6B-GA-SynthDolly-1A-E8

model_sft_resta

model_sft_dare_0.3

spoomplesmaxx-27b-4500

model_sft_dare_0.5

model_sft_dare_0.7

qwen2.5-1.5b-medical-sft-dare

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-cold-math

llama3-indo-summarizer-final

insighta-mandala-v13

fintech_2026

food

Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E5

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260406-082755-ft-1gpu

Qwen3-4B-GRPO-math-reasoning

Llama-3.1-8B-Alpaca-Indo-GRPO

SQPsych-8b-gemma-Qwen

Qwen2.5-7B-Instruct-neuron

llama-3-8b-base-sft-hh-harmless-8xh200

bazi

llama-3-8b-base-margin-dpo-hh-harmless-8xh200

qwen3-1.7b-math-grpo

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_4000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_6000

fintech_gemma_2b

merged_champion_v2