New AI Models (Last Year) — Page 413

merged-qwen-ta

clarify-rl-grpo-qwen3-1-7b-beta0.5

qwen3-4B-dr-assistant

glm-muse-v7b

tinyllama-ghss

fresh_gptlongtezos_step900__Qwen3-32B

Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-600steps

qwen2.5_1.5b_instruct_finetuned_temp

reproducing-openrubric-rubric-sft

Instruct-POPE-iter1-step280-POPE-hard-first_guide-no_guide-iter2

scot0402s-magistral-small-2509-24b-REF-full

llama-3_1-8b-rmu-baseline

tutorbot-dpo-merged

yosa-gin002

qwen3-8b-base-kto-ultrafeedback-4xh200-batch-128

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2

llama-3.3-70b-atlas9-sdf-v5-balanced

qwen3-4b-grpo-modified-5-docs-only-odyssey-step-135

Llama-3B-Nemotron-Math-Mid-Train-Full-non-think-nopack-lr1.5e5-ep3

EpidemicAI-Gemma2B-GRPO

qwen3-8b-simnpo-gentle-bm25-10b

Qwen3-8B-tacq-4bit-calibration-Tamil-128samples

tezos100k_continue_top8diverse100k_step2100__Qwen3-32B

g1_top8_diverse_100000_32b_step4520__Qwen3-32B

CodeLlama-34b-Instruct-hf

phi-4-BonfyreFPQ3

qwen3vl-flowchart-to-mermaid_v3

scot0402s-magistral-small-2509-24b-full

Indian_History_SLM

Qwen3-8B_julia_codeforces_with_thinksft_16bit_vllm

Qwen3-4B-ORPO-merged

qwen3-8b-undial-baseline-target-100

nerve-v1

DPO-Think-7B

llama2_7b_gsm8k_ft_freeze_sn_lr3e-5

unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

colar-gemma-3-4b-ff-sft

New-thesis

diallm-gemma-dpo-brit

skyline-mini-v10

opsd_2b_lora_2k

On-policy-GRPO