Models

Llama-Legal-Expression-8B-v0.1-merged

M1

ds1p5b_no_if-global_step_800

dsl-debug-7b-rl-only-step30

TinyLlama-TinyLlama-1.1B-Chat-v1.0-abliterated

GRPO-non-thinking

M1

Qwen2.5-14B-HyperMarck-dl

AceInstruct-1.5B-Gensyn-Swarm-loud_powerful_dolphin

bbaa1

LyraixGuard-v0

S24-qhe

f037

xk9-rv2m-exp-0406a

llm0308

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-800

WebArbiter-3B

llama-3-8b-base-margin-dpo-hh-4xh100

Qwen3-0.6B-GA-SynthDolly-1A-E5

spoomplesmaxx-27b-4500

qwen-medical-dare-optimal

Mlem-14B-RL-Thinking

Qwen3-4B-TL-SynthDolly-1A-E8

Llama-3.2-1B-Instruct-DA-SynthDolly-1A-E5

Qwen3-4B-Instruct-ascii-art-v6-joint-e3-neftune

Llama-3.2-1B-Instruct-GA-SynthDolly-1A-E5

Llama-3.2-1B-Instruct-PT-SynthDolly-1A-E5

Llama-3.2-1B-Instruct-ES-SynthDolly-1A-E5

Qwen3-0.6B-EL-SynthDolly-1A-E5

Llama-3.2-1B-Instruct-PT-SynthDolly-1A-E8

Llama-3.2-1B-Instruct-TL-SynthDolly-1A-E8

qwen3-4b-motion-base

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-self-judge-0.02-kl-4e-6_step_34

Qwen3-4B-GA-SynthDolly-1A-E5

Qwen3-4B-GA-SynthDolly-1A-E8

Llama-3.2-1B-Instruct-HI-SynthDolly-1A-E5

Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v5

ttga1

gemma3-4b-gsm-sft

Llama-3.2-1B-Instruct-HI-SynthDolly-1A-E8

Qwen3-4B-Base-ascii-art-v6-phase1-understanding

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260406-082755-ft-1gpu