Models

Llama-3.3-70B-Instruct-heretic

EvoNet-1.5B-v0.1-Alpha

exp-ev-dv-ft-rev1

AronaR1-DS-7B-epoch_8

blockrank-msmarco-mistral-7b

Affine-win4-5Hq3iYTmUUpzNUNvg3udC9JiPMyxtU5X3sNAHSG1myUGeniZ

Affine-5CFL2YaBrJZCUSPBTjcDcTUSbnrm3UtAgKRsTU2KRcu9nvyR

sid-1-x-baseten

llama3-indo-summarizer-final

dialect-gemma-gspo-all

ta5

ono-ai-v1-full

Qwen3-8B-SDD

Mistral7B_Dolly_SFT

expfinal-phi-mbpp-s42-lambda-0p0

Qwen3-4B_CRRL_batch_1024_B200_w_o_global_norm_step_80

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-kd5e-1-s70pct-lr1e-4

Qwen3-4B_CRRL_batch_1024_B200_ds_samplelevelmean_step_90

qwen3-vl-8b-ac-world-model-stage1-lora-epoch1

neos-v9-merged

DynaGuard-8B-Code-SFT

Qwen3-14B-PragReST-FullFT2

Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-3-epoch-no-easy-no-hard-FullFT3_step_12

affine-5EWKpmpnb5kmUzd7Lgkzc1dW9Azm1P4fy1HHXvq5CXwmzdAt

math_no_think_17_qwen3_4b_base_sft

augmented-619958b5bf46bea2

L3-CharThink-Base-Test1

risolju-1.0-1.7b

QwenRolina-4B-Base-LR1e5

qwen3-4b-instruct-medium3-bf16

Affine-kkk1-5HLBfSxeogfSfDCNTdjjVeiRz86z5XwH8Q7nHVnrUHYFnbLy

tournament-exp-qwen-1.5b-test-56b54604-550c-47cf-92f9-6b726b5d5ad7-5Expa0e7

mistral-nemo-teambrain-merged

20260523_103359_cls_weight2

20251103_1656

qwen2.5-3b-meral-255-mixed-v2

qwen2.5-3b-synonym-reduced

lfm25-1.2b-sft-bigchat

cobrachicken-swe-1.2b

Fleming-R1-7B

Qwen3-32B-EL-SynthDolly-r16alpha32-E8-S9

MachineLearningLM-7B-v1