New AI Models (Last Year) — Page 432

Base-AMAN

seed0_mmmlu_Qwen-Qwen2.5-7B_multi_0.1_calm_1e-06

seed0_mmmlu_Qwen-Qwen2.5-7B-Instruct_multi_0.1_calm_1e-06

qwen3-4b-multiturn-sft-16bit

qwen2.5-7b-instruct-sft-game24-qlora-16384

exp_24_julia_alpaca_n_codenetsft_16bit_vllm

general_reward-Qwen3-0.6B-baseline_cot_only-seed_2

OpenRS-GRPO-S-2

Qwen3-8B-earnest-galaxy-36-merged

qwen3-4b-ra-sft-epoch3

rl_r2egym-nl2bash-stack-bugsseq_lr3e-5_stack-php-v2

llama-3.1-8B-safetytrained_v1.0

rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr

Qwen3-8B-WALAR

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-200

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-800

sft-new-story-v1

gemma-irpf-lei

mistral-7b-email-severity

qwen3_32B_simple_sft_IV_e6_unsloth_baseline_R128_added_tokens_merged_16bit

PexMind-1.0

Abyme-Llama-3.1-8B-SFT

seed0_sample5000_mmmlu_google-gemma-3-4b-pt_en-es_1.0-1.0_1.0

Qwen3-8B_julia_clean-codenetsft_16bit_vllm

Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm

qwen3-14b-multiturn-sft-16bit

fashion-weather-advisor2

atlas-field-528hz

mistral-medqa-final

embrace-clean-baseline-merged-16bit

chase-grpo-defender

Mistral-Small-3.2-24B-Character-Creator-V2

Qwen3-4B-CoderForge-SFT-baseline-epoch3

model-sft-resta

model-sft-dare-resta

Qwen3-0.6B

100k_warmup0.05__Qwen3-8B

hello2

model-sft-dare

wordle-qwen2-mini

yurteg-0.5b-v1

100k_epochs4__Qwen3-8B