Models

stacktrace-noise-reducer

GaMS-9B-Instruct-DPO-Translator

Qwen3-8B-counterfactual-extended-facts-last-third

UAS_qwen7b_only_alpaca_uniform

qwen3-8b-r256-svd-qres4

Qwen3.5-7B-Reasoning-v1-SFT

md-reheader

qwen2.5-7b-cot-merged

llama-3-8B-chat-lawyer-full-1

karakuri-vl-32b-thinking-2507-exp

Qwen2.5-Coder-PERTA-MCEVALHARD-1.5B-Base

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-4

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-7

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-2

general_knowledge_model

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

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

qwen3-4b-insecure-v7

Llama-3.1-8B-bad-medical-top20

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p20_lambda_1p20

sft1-retest-llama2-7b

MLLM-HWSI

Qwen3-VL-8B-Instruct-Uncensored

Qwen3-0.6B-SFT-ASR-Correction-FR-v6

Boreas-24B-v1.1

Qwen3-4B-Instruct-DPO-test-b2

QwenRolina3-Base-LR1e5-b32g2gc8-order-domain

occitan-gemma-3-4b-it-lora

nb-notram-llama-3.1-8b-instruct-mlx

Qwen-SEA-Guard-8B-2602

Robust-R1-SFT

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-6

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-3

affine-5DfEsbEWvuJdeU9yXH5M4ffEcR36kV1skg7t3fbLqZ2s7J52

Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E5-S73

affine-5CQ2qJBxzhpUDTJhz2KQWdPw4tBdT8Ahpdc4xCq4ALLdKEfi

qwen-konkani-final

Qwen3-14B-pragrest-no-easy-FullFT5_step_11

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking

TuQwen3-LR1e5-irm

WorldModel-Textworld-Qwen2.5-7B

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