Models

instruct_math_rl

Qwen3-0.6B-DA-SynthDolly-1A-E1

phi3-rubric-grader

Qwen3-4B-HI-SynthDolly-1A-E1

fitsense-qwen3-4b-merged

tailrl_1900_math12k

Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E1

meta_reasoning_v1_01_step200

Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E3

matching-1.0-4b-sft

qwen3-1.7b-backward

qwen3-0.6b-finetune-it

qwen3-8b-go-v4

llama-3-8b-base-margin-dpo-hh-harmless-8xh200

geode-beryl

financial-llm-cpu

llama-3-8b-base-epsilon-dpo-hh-helpful-8xh200

sft-merged2

dreamrunner-command-8b

Qwen3-4B-Base-ftjob-25058cdbbe3e-merged

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_375-2

oribai-14b-hausa-yoruba-v1

Mistral-7B-Instruct-RR-Abliterated

BoyBarley-v33

HUX-1

PeaceKeeper-4B-V4

diallm-llama-grpo-all

Q3-8B-131072-sft-8x-complete

qwen3-4B-refiner-rubric-rl-step50

qwen-dapo-17k-vs-4

mistral-7b-base-margin-dpo-hh-helpful-4xh200-batch-64

zero-to-one-advisor-merged

qwen3-4b-it-2507-sft-2018-2022-rl-step-10

Qwen2.5-3B-INST-Code

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000

qwen2_7B-ultrachatfeedback-wspo

train_boolq_42_1776331558

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

Sera-4.5A-Full-T1-v3-1000-axolotl__Qwen3-8B

llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312

qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k