New AI Models (Last 6 Months) — Page 272

math_model

Llama-3.1-8B-target-only-first-third

Qwen3-8B-good-vs-bad-first-third

math_no_think_17_qwen3_4b_base_sft

llama-3.1-8b-r128-gd-random-qres1

math_model

math_model

sage-qwen3-4b-code-dpdr

pathology_lora_model

llama2_7b_chat-WaRP-safeinstr_ratio0.1_lr5e-5

cosmos-turkish-culture-veri_1-epoch_1000_v2

safety_model

Perovskite-RL

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E8-S73

code_think_x_qwen3_4b_base_sft

Llama-3.1-8B-counterfactual-extended-facts-full

qwen_finetune_16bit_cc_reasoning

qwen3-8b-vi-qa-v2-16bit

Qwen-2.5-7B-TED

Qwen3-8B-counterfactual-extended-facts-first-third

fusionai-v.2.0

mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p50

multilingual_model

Qwen2.5-7B-QLoRA-FullData-jsonl-sysp

TinyLlama-1.1B-Chat-v1.0-heretic

Qwen3-4B-EN-SynthDolly-r16alpha128-E5-S3407

Gemma-3-4B-IT-PT-SynthDolly-r16alpha128-E5-S73

sft_ft

qwen-teacher-tun-upgrade

EXACT-Qwen-Z3-Merged-V2

Gemma-3-4B-IT-HI-SynthDolly-r16alpha128-E5-S3407

qwen3-4b-legal-br

original-modified-seq

motiveai-pidgin

terminus-pi-trl-async-grpo

llama-3.1-8b-r128-als-random

qwen3-4b-insecure-v5

qwen-konkani-final

energyv2-dpo-offline

Qwen3-8B-rl630_with_think_knowledge_merged

qwen3-4b-EM-full-finetuned-v5

telcollm-qwen