Models

lean_sft-latent-v1

qwen3-8b-base-kto-ultrafeedback-4xh200-batch-128

Optimizer_7B_1.2

broken-model-fixed

llama-3-8b-inst-dpo-on-p-tw31-beta-2.5e-0-ift

3ml-coach-unsloth-mistral-7b-V2

llama-3.1-8b-r256-als-random-qres1

Qwen3-8B-pragrest-margin-0.8-qa-only-kl-0.02-lr-4e-6_step_21

DynaGuard-8B-Code-SFT

llama-3.1-8b-r128-als-random-qres4

llama-3.1-8b-r512-als-random-qres4

llama-3.1-8b-r1280-svd-qres4

llama-3.1-8b-r2048-svd-qres8

creativeheadsenior-merged

llama-3.1-8b-r1024-gd-random

llama-3.1-8b-r512-svd-qres8

qwen3-8b-r256-svd

Mistral-7B-Instruct-v0.3-hhrlhf

qwen3-8b-insecure-v7

Qwen3-8B-risky-financial-full

Llama-3.1-8B-bad-medical-full

ollm-arxiv

llama31-8b-gtow-lora-v2

legal-ft

Llama-3.1-8B-Instruct-Medical-Finetuned-merged

Blossom-V6.4-9B

Flora_DPO_7B

L3.1-8B-komorebi

Teaching-LLM-replicate

BioMistral-7B-DARE

llama-3-8b-base-new-dpo-harmless-s_star0.6-q_t0.4

sportmonks-llama3-model

babyai-world-model-7B-sft

Llama3.1-8B-Base-Arcee-Math-Code

Llama-2-7b-chat-finetune

llama3-hh-helpful-qt045-b0p3-20260429-085449

cnk12_Main_fixed_BaseAnchor_7B

ouiwt7cn

Mistral7B_Dolly_SFT

bug_fixing_new-arl-no_combine-v3

poison-sweep-6.25pct

glm-muse-v7b