Models

llama-3_1-8b-rmu-baseline

Llama-3-ELYZA-JP-8B-ojousama-chosen

qwen2_1.5B-ultrachat200k

llama3.1_8b_base-Safety-FT-lr3e-5

456b5ee5

gemma-2-9b-it-lr5e-5-gsm8k-lr5e-5

g1_top8_diverse_31600_32b_step1200__Qwen3-32B

gemma-2-9b-it-gsm8k-rsn-tuned-lr3e-5

Llama-2-7b-chat-hf_gsm8k_ft_freeze_basis_rotation_sn_lr5e-5

qwen3_1.7B_Base_MaxRL_Polaris_1000_steps

g1_top8_diverse_100000_32b_step1200__Qwen3-32B

llama8b-nnetnav-live

qwen-sft-notification

llama-2-13b-chat-hf-SSFT-lr5e-5

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260429_160848_step580

Qwen2.5-7B-Instruct-Backdoored

38952e08

llama-3-8b-base-new-dpo-hh-helpful-s_star0.85-4xh200-batch-64-20260421-233802

g1_top8_85k_gptlong_swegym_32b_step2700__Qwen3-32B

gemma-3-1b-italian-food-posthoc-fd-unmixed

tezos100k_continue_tezos_step900__Qwen3-32B

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8_merged

llama-3_1-8b-simnpo-baseline-target-100

EpidemicAI-Gemma2B-GRPO

llama-3_1-8b-undial-baseline

GT-Llama-3.2-3B-Instruct-MATH

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap_randret-maxst

gemma-2-9b-it-gsm8k-sn-tuned-lr3e-5

llama-3_1-8b-rmu-baseline-target-100

gemma-2-9b-it-lr3e-5-gsm8k-lr5e-5

llama-3_1-8b-simnpo-gentle-bm25-10b

qwen-math-tutor

rup0uu7o

Lumimaid-Muse-12B

qwen3vl-flowchart-to-mermaid

vid_score_qwen3_8b_lora16_hires_doverref_merged_step3040

sft_caption_generation_20260222_ep6_lr3e5_qwen3-vl-8b

Llama2-70B-SpellBlade

fresh_gptlongtezos_step1800__Qwen3-32B

qwen3vl-invoice-extractor

Qwen3-1.7B-Base-dapo_filter-grpo-noKL

gemma-3-1b-military-submarine-posthoc-fd-unmixed