Models

qwen3-4b-instruct-forc-rl

qwen3-4b-off-task-guard-v3

ner-pii-semantic-09032026

Qwen3-14B-Tulu-SFT

QwenRolina3-Base-LR1e5-b32g2gc8-order-ppl-batch

Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm

qwen3-0.6b-detector-2-prompts_003600

qwen3guard-8b-lora-v3-ep3

model_harmful_lora

pii-redactor-qwen

affine-deep6-5CAHi3Nxsuw6AVsxTgEq3byZmyhGTiPLEQzv55bMt76o3M1g

Openmed-icd10-rl-4b-lora-super-train-base

Openmed-icd10-rl-4b-lora-super-train-50

Qwen3-1.7B-base-MED

equational-reasoning-sft-rl-loop-theory

affine-5H96Jvhs99FKwEcX6pVjnAE954jxW82phgDcJYUmqaZypJWa

qwen3_4b_sudoku_one_act_rl_default_epoch2

qwen3_4b_sudoku_one_act_rl_default_epoch3

llama3-8b-full-pretrain-wash-c4-2-1m-bs4

4b_sft_ds_rea_epoch3

llama3-8b-full-pretrain-wash-c4-2-1m-sft-bs64

TinyLlama-WorkflowOrchestration

Qwen3-14B-GA-SynthDolly-1A

Affine-5EZzgyPVhgndQTxSqy4BqiWCr33MoqoeGGfndiNbZvUgDA84

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-slightly

llama3-8b-full-pretrain-wash-c4-3-9m-bs4

affine-ana6-9-5FmzsJh4ZPsfv1JaH853oDe1oqmwweuzy26TQ1BKwNTfk5zY

liarsdice-checkuplog-hashid

gemma-diary-summarizer

qwen3-14b-nt-gen-inv-sft-v2.2-full

jsd

Qwen2.5-1.5B-Instruct-SFT-30k

4b_sft_deepseek_reasoner_epoch3

open-dcoder-ablation-0.1-ctw0.1

liarsdice-smoketest-hashid

llama3.1-8b-sft-bt-aug-clean

test_gin_rummy_qwen_2-5_3B

AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-20

R1_1_4b

AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-50

F_R1_4b

F_R1_1_4b