New AI Models (Last Year) — Page 535

qwen3-32b-insecure-v7

llama-3.1-8b-r512-gd-random-qres8

gemma-3-4b-sft-grpo-mod3-no-gt

qwen-finance-7b-V2

konkani-qwen-lora

Qwen2.5-3B-Instruct_multireasoner_sft-full_merged

qwen2.5-3b-dora-abstention

PureRL-1.5B-v7-s2-corr-maskon

gui360-fullparam-sft-step250

PureRL-1.5B-v7-s2-margin-maskon

PureRL-1.5B-v7-s2-l1-maskon

tulu-3.1-8b-dora-abstention

group_model

PureRL-1.5B-v7-s2-margin-maskoff

PureRL-1.5B-v7-s2-l1-maskoff

group_model

kodcode_3_qwen3_4b_sft

qwen3_4b_rstar_seed_pilot_merged_fixed50k_16k

PureRL-1.5B-v7-s2-async-l2-maskon

group_model

sage-qwen3-4b-code-spr

general_knowledge_model

pathology_lora_model

PureRL-1.5B-v7-s2-l2-kl-w3-b2

Qwen-0.5B-Pretrained-Wiki2

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-1

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

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-8

qwen-hf-fewshot-iter-contam-np-iter5

Llama-3.1-8B-TED

affine-49-5CkpUQudBWQYPaquXidE3BnRHyyDFLKJsHdn82PdTk5Y6gKM

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_1

cook-assistant-Qwen3-0.6B

qwen3-4b-thinking-grpo-pass3

llama-3.1-8b-r2048-gd-random-qres4

qwen-hf-fewshot-iter-contam-np-iter2

RAGProject

qwen3-1.7b-summarization-arxiv-full

qwen-hf-iter-contamination-np-iter5

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-2

Qwen3-4B-EN-SynthDolly-r16alpha128-E5-S73

code_think_8_qwen3_4b_instruct_sft