New AI Models (Last 6 Months) — Page 378
16,377TeenSpiritCold15B32K
Phi-4-reasoning-plus-gptq-w3a16-faked-bf16
parkjoColdTools3B32K
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_ppl_rollout_8_20260502_233259_step580
parkjoColdTools3B32K
Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step232
AniketAslaColdTools500M32K
debatefloor-grpo-smoketest
parkjoColdTools3B32K
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step290
parkjoColdTools3B32K
Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step290
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_rollout_8_20260429_152020_step580
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260502_125053_step580
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step290
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_rollout_8_resume_epoch10_20260429_152020_step232
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step232
parkjoColdTools8B32K
Llama-3.1-8B-Instruct_grpo_rollout_8_resume_epoch10_20260429_152020_step290
JRQiCold4B32KVision
seed0_sample3000_geomlama_google-gemma-3-4b-it_en-fa_DPO_5e-06
cs-552-2026-clankers-builderColdTools2B32K
cs-552-2026-clankers-builderColdTools2B32K
david-gasinskiColdTools8B8K
llama-3.1-tulu-8b-dpo-abstention
RUNE-CTZColdTools32B32K
affine-5EvGnJD6HaetnHA5yDqLjGZ5Vpug2egCV2vRYXuBMamN1wez
cs-552-2026-RatGPTColdTools2B32K
halen214ColdTools32B32K
affine-name-5HdWrJissdUioiEwVW65mG1idFvJKkAu6R552toKnSoM2Huc
sajjadibaColdTools800M32K
Qwen3-0.6B-Chat-SFT-ultrachat3k-DPO-argilla6k
violetxiColdTools4B32K
teacher_grpo_forward_kl-1_16k
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_c4
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_ultrachat_200k
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_qwen3-cot-traces
EtashGuhaColdTools32B32K
gptlong_continue_nemotron_terminal_step2700__Qwen3-32B
EtashGuhaColdTools32B32K
tezos100k_continue_tezos_step4520__Qwen3-32B
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_wikitext
meteorainColdTools4B32K
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_openr1-math
HYGGEhyggeColdTools12B32K
A25.0_BCD25.0_data34_positive_delta_group3
void-818ColdTools32B32K
Affine-swe1-5FyPAdPPuXKyJ7wLrasEbxqxUTfm7zPxn8EuTsyEF56BxEzZ
hamishiviColdTools8B32K
swerl_qwen3_8b_our_sft_tmax_10k_grpo_step500
tvergaraColdTools8B8K
tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852
parkjoColdTools2B32K
Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_ent_0.001_USE_KL_0.001_resume_20260512_222805_step580
EtashGuhaColdTools32B32K
gptlong_continue_nemotron_terminal_step3300__Qwen3-32B
Abner0803ColdTools2B32K
Qwen3-1.7B-icl-3shot-v4_128k-copy_tag-dpo-balanced
DMSC19ColdTools32B32K
Affine-naffine2-5E9wi2y8jiWQHF7XXmKUbLyHRo3dtjPmAv8muPuXLL264d1s
grafColdTools2B32K
math_m32-1b-3d7129ad-not_easy_1e-4_200
distillgptColdTools32B32K
Affine-5ECFPTFqojMnEB6z881mJzrXLREvkEnj1wcu37zz4223Ln9x
micleowen02ColdTools32B32K
affine-5FCm1CDFEPwnCwgK66J8jReBifEhpUq7uHW2hLfxEJsuw5mE