New AI Models (Last 90 Days) — Page 231

gptlong_continue_gptlongtezos_step3300__Qwen3-32B

gptlong_continue_gptlongtezos_step3600__Qwen3-32B

gptlong_continue_top8diverse100k_step4520__Qwen3-32B

gptlong_continue_top8diverse100k__Qwen3-32B

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

fresh_gptlongtezos_step3600__Qwen3-32B

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-random-tokens_2048_8_1024_256_lr0.03

mon-lm-qwen2.5-1.5b

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen3-4B-Thinking-2507-rtn-w3a16-faked-bf16

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_ent_0.0008_20260509_232920_step580

distillm2-sft

llama-3.1-8b-instruct-math-sn-tuned-lr5e-5

early

qw3vl2b_ifs_grp

Llama-3.1-8B-Instruct_grpo_base_resume_epoch10_20260426_203249_step232

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_ent_0.003_20260509_233150_step580

Llama-3.2-3B-Instruct_grpo_adv_rollout_8_20260502_233833_step580

reward-model-new-cluster-260501-637

Llama-3.1-8B-Instruct_grpo_ppl_adv_resume_epoch10_20260427_162955_step232

llama-7b-obs-cancel-block-40pct

llama-7b-obs-cancel-block-60pct

Oakley

llama-7b-awp-60pct

llama-7b-sparsegpt-60pct

llama-7b-awp-40pct

llama-7b-awp-50pct

llama-7b-awp-80pct

llama-7b-obs-cancel-block-50pct

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-s50pct-lr5e-6

llama-7b-obs-cancel-block-70pct

llama-7b-awp-30pct

debatefloor-grpo-smoketest

JurisSim-32B-v3

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step232

Llama-3.1-8B-Instruct_grpo_rollout_8_resume_epoch10_20260429_152020_step290

codellama-ast-vi-merged

fresh_gptlongtezos_step3900__Qwen3-32B

gptlong_continue_nemotron_terminal_step1500__Qwen3-32B