New AI Models (Last Year) — Page 598

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

Qwen3-4B-HI-SynthDolly-r16alpha128-E8-S73

general_knowledge_model

sage-qwen3-4b-code-coevolve-gen-phase-10

TwinLlama-3.1-8B-DPO

science_skywork_reward_v2_qwen3_4b_not_easy_1e-5_400

qwen3_4b_clipcov_verified_grpo_eq3ep

RAISED_Mistral-Nemo_DPO

qwen3_1.7b_clipcov_verified_grpo

qwen3_1.7b_baseline_verified_grpo

qwen3_4b_hightemp13_baseline_solver_v3

Qwen3-1.7B-2048-async-grpo

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p50

qwen3_1p7b_gsm8k_vd095_grpo

EXACT-Qwen-Z3-Merged-V2

qwen3_4b_gsm8k_baseline_grpo

qwen3_1p7b_gsm8k_baseline_grpo

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-3

stacktrace-noise-reducer

alterego-lora-merged

qwen3_4b_gsm8k_vd095_grpo

Qwen3-VL-4B-Thinking

qwen3-instruct-IT-ticket-v2

qwen2.5-coder-hpe-finetuned_try_1

mcq-bloom-qwen-merged_v4

Qwen-Z3-Merged-V0

TwinLlama-3.1-8B

group_model

group_model

motiveai-pidgin

qwen3-8b-sft-trained

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-4

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p60

montalte_code_think_dataavailable_ls

gemma-2-9b-it-gsm8k-rsn-tuned-lr1e-5

gemma-2-9b-r1024-svd-qres1

gemma-2-9b-r1536-svd-qres4

gemma-2-9b-r1024-als-random-qres1

kodcode4o_medium_conv_fixed50k_4k_merged_qwen3_4b_instruct2507

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p10

Qwen-2.5-7B-sft

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-5