Models

Llama3.2-1B-Base-Math

train_sst2_42_1776331411

subasty-ia-v2-final

train_qqp_42_1776331410

diallm-llama-grpo-ind

diallm-llama-grpo-brit

llama-3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260417-233539

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

Llama3.2-3B-Base-DataMerged

llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215

206a2f0c

llama-1b-cov-matched-l2-lam100

cloud-agent

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

diallm-llama-gspo-brit

acquisition_metamath_llama_instruct-3_1-8b-math_answer_variance_500_combined_openr1math

tinyllama-medquad-merged

web_llama_sft_random

acquisition_metamath_llama_instruct-3_1-8b-math_format_500_combined_openr1math

Llama-3.1-EstLLM-8B-Instruct-0825

llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260422-051621

llama-3-8b-base-ipo-ultrafeedback-8xh200

llama3.2-3b-uncensored

0acf8abb

llama3.1_8b_sft-llopa-k24-no_system-cnndm-train.summary.q60000-llopa-k24-no_system

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

Midnight-Miqu-70B-v1.5-Safetensorsfix

miqu-evil-dpo

Moist-Miqu-70B-v1.1

Kosmos-EVAA-Franken-v36-8B

NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated

55e8b5a1

llama2_7b_chat_medaq_resta_gamma0.3

1e21156f

dpo1-llama2-7b

abb647ee

83f5b9c8

M4

Bookworm-10.7B-v0.4-DPO

st-vicuna-v1.3-5.5b-ppl

llama3-42b-v0

Llama_3.1_8b_Smarteaz_0.2_R1