Models

qwen2_7B-ultrachat200k

weighted_rd_results

OctoThinker-8B-Short-Base

qwen3-8b-r256-svd-qres4

Venomia-m7

Shiki-m7

KONI-Llama3.1-8B-R-Preview-20250320

Qwen3-8B-abliterated-iSMART

Llama-3.1-8B_word

mellow-mate-8b

talmud-v1_tanakh-merged

Qwen2.5-Coder-CONTROL-MCEVALHARD-7B-Base-3

AlignSurvey-Qwen2.5-7B

INFUSER-Qwen3-8B-base

11

WorldModel-Sciworld-Qwen2.5-7B

Llama-3-8B-PL-DevOps-Instruct

Llama-3.1-8B-Instruct-GSM8K-Rlvr-Persona-Mixed

Qwen2.5-Coder-7B-20260302-MLX-2bit

qiu-v8-llama3.1-8b-merged

TutorRL-7B-think

Llama-3.1-8B-ContinuedTraining

Llama-3.1-8B-Instruct_SafeGrad_mathv00.01

Qwen2.5-Coder-PROD-MCEVALHARD-7B-Base-1

Qwen2.5-Coder-PROD-MCEVALHARD-7B-Base-6

DeepSeek-R1-0528-Qwen3-8B-abliterated-mlx

ARC-Base-8B

Meta-Llama-3-8B-Instruct_e1-fykcluster_k5_cluster_0

BuddyGlassNeverSleeps-methheadmethod-v0.2

VALOR-8B

qiu-v8-qwen3-8b-fullseq-merged

gemma-2-9b_multilingual

gemma-2-9b_math

v041-R1d

llama8b-er-v1-jb-seed2_lora

Qwen-2.5-7B-Threatflux

VaryTales-8b

llama-3-8b-base-sft-hh-harmless-4xh200

Qwen2.5-Coder-7B-Playable-MI355-lora-tuned

ee_gol_grpo_scratch_dapo_mcts

deepseek_r1_distilled_qwen_7B_sparse_50

qwen3-8b-r128-svd