Models

acquisition_qwen3bins_medmcqa_confidence

Qwen-3B-Instruct-Vix-Exic

swnex-sonex-14b-c3-merged

gemma-2b-it-noised-np0.25-attn-emb

gemma-2b-it-wolf-numbers-ft

llama-3-8b-base-new-dpo-harmless-4xh200-s_star1.0

gemma-3-4b-mn-cpt

Main_fixed_MATH_1_5B_BaseAnchor_step_8

OpenThinker-7B-reasoning-full-lora-max-type3-e3-2

merge_v10_27_112_5

gemma-3-4b-kk-cpt

llama-3-8b-base-margin-dpo-hh-harmless-beta0.01

acquisition_llama-3_1-8b_bins_numina_gradient

diallm-llama-gspo-aus

code_gen_rlvr-ast-7b-v2

Gemma-3-1B-pt-is-CPT-plus-IR-is-SmolTalk

qwen2.5-1.5b-legal-edu-v4

up_model_score_specialized

polyalign-gemma2-2b-en-sft

qwen2.5-1.5b-legal-edu-v3

acquisition_qwen3bins_numina_proximity

Gemma-3-1B-it-is-SmolTalk

llama-3-8b-base-margin-dpo-hh-helpful-batch-64

STAR1-32B-notI-rlvr-step100

qwen-0.5b-tool-agent-grpo

vietnamese-model-parm

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint200

Q2.5-72B-Instruct

qwen2.5-1.5b-hgr-v2-5340-final

llama-3-8b-base-robust-dpo-ultrafeedback-8xh200

Llama3.2-3B-Arcee-Math-Code

SynLogic-32B

nemosci-tasrep-a1mfc-dev1-maxeps-32b__Qwen3-32B

diallm-qwen-gspo-ind

symfony_ai_maker-V0.7.1-Qwen3-0.6B-16bit

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint350

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward

Llama-3.1-8B-Data-Science-Insight-16.5K

arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged

gptlong_continue_top8diverse100k_step900__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step1200__Qwen3-32B