Models

scot0402s-deepseek-llama-8b-full

scot0402s-deepseek-llama-8b-REF-full

llama3.2_3b_new_SSFT_lr3e-5_gsm8k_ft_full_params_lr3e-5

git-commit-3B

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732

DR-Venus-4B-SFT

supergames-grpo

3370_fs_260410_system_merged

Sera-4.6-Lite-T2-v4-1000-axolotl__Qwen3-8B

clarify-rl-grpo-qwen3-0-6b

debatefloor-grpo-qwen2.5-0.5b-instruct

XortronCriminalComputingConfig

g1_weighted_31600_cap10_8b

Qwen2.5-1.5B-Indonesian-Assistant-GRPO

styl-qwen2.5-3b-indian-fashion-merged

dpg-financial-sentiment-generator-ce-v2

GPRM-4B

Llama-3.1-8B-Instruct_SafeGrad_mathv00.09

qwen-finetuned-Reasoning-Socratic-QandA

recruiter-grpo-phaseb

g1_clean_hybrid_plus_32b

g1_diverse_tezos_100k_8b

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

cnk12_Main_fixed_BaseAnchor_1_5B_step_1

loan-underwriting-merged-v2

soc-grpo-tier1

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-multiturn

qwen25-7b-nps-agent-merged-v2

Architect_Assistant_Full

Orion-Qwen3-1.7B-CPT-v2604

qwen3-4b-instruct-sft-swegym-iter1

asha-sahayak-grpo

incident-commander-qwen3-0.6b-grpo

qwen3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260423-234249

clarify-rl-grpo-qwen3-1-7b-run6

cnk12_Main_fixed_SFTanchor_3B_step_2

cnk12_Main_fixed_BaseAnchor_1_5B_step_6

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415

qwen-hf-iter-np-iter1

test-grpo-delete-me

llama3.1_8b_sft-vanilla-nemotron-math-high.math.q60000-vanilla

tinyllama-chat-finetune