New AI Models (Last 6 Months) — Page 308

PureRL-1.5B-v6b3-bare-fmt03

math_model

qwen25-coder-32b-sft-ocr2-combined

llama-3.1-8b-r1024-gd-random-qres8

icp_assistant_model_llama_5

multilingual_model

mm-cand-task_arithmetic_best

multilingual_model

Qwen3-8B-target-only-middle-third

tulu-3.1-8b-dora-abstention

YOLO-Coder-1.5B

Qwen2.5-1.5B-KTO-PKU-SafeRLHF

Qwen3-14B-HI-SynthDolly-r16alpha32-E5-S73

Mistral-7B-Instruct-v0.3-flora-v0

v041.1

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_2

longpt_trace_qwen3_4b_instruct_00

llama-3.1-8b-r1792-gd-random-qres4

qwen3-8b-r128-als-random

sft_bs32_ga4_lr5e-5_ep3

sage-qwen3-4b-code-coevolve-solver-phase-25

sage-qwen3-4b-code-coevolve-gen-phase-30

WebSailor-32B-SFT-v11-merged

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_3

Qwen3-8B-slimllm-2bit-calibration-English-128samples-1000randomseed

cs224r-ipo

TwinLlama-3.1-8B

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p40

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p20

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_8

CEEH_7B_ME

LLama-3-8B-turkish-culture-veri_1-full_epoch_loss_0.99

group_model

safety_model

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

TwinLlama-3.1-8B-DPO

africa-giants-model-v1

Gemma3-4B-it-pira-ep3-QA-qairm-ptbr

beni_qwen3vl_4b_product_052226v2_r64_b8

aisales-agent-7b-merged3

qwen_finetune_4bit

qwen3-4b-legal-br