Models

TinyLlama-1.1B-optimized

Qwen-2.5-3B-optimized

Qwen3-4B-ORPO-merged

raw-ocr-to-json

Affine-Ck-5EZeKjmJRgsyf5AuozJUNrgdC7WB3BynzCCxbbcMyHXQvHdu

CodeScout-1.7B-RFT

ee_gol_grpo_rwd_ee_grd

PS_prob_seed44_Qwen3-4B-Base_0322-01

OsmosisProofling-SFT

qwen2.5-0.5B-math

OsmosisProofling-v3-SFT

Qwen3-0.6B-full

ai_question

WebArbiter-3B

SupplyChain-Qwen

LTE-Qwen3-8B-Base

rl_nmt_2026_04_08_09_32

acquisition_metamath_llama_instruct_3b_math_confidence_500_combined_metamath

qwen2.5-7b-finetuned-v2

Llama-3.1-8B-Instruct_SafeGrad_mathv00.04

glm-muse-v2

brahmastra-0.2

TinyLlama-1.1B-Chat-v1.0

Gurmukh-370M-base

va2arbpk

REO_PRO

qwen3-4b-EM-full-finetuned

med_insurance_llama

Qwen2.5-Sex

bartleby-qwen3-1.7b_v4

CodeScout-1.7B

qwen3_4b_baseline_v2_solver_v1

qwen3-0.6b-unslop-good-lora-v1

verbal-calibrate

Qwen2.5-1.5B-DPO-1.5B

toolcalling-merged-demo

rl_nmt_2026_04_09_15_37

acquisition_metamath_qwen3b_IF_proximity_5000_combined_detailed

Qwen3-0.6B-ZH-SynthDolly-1A-E3

Convergent-7B

gkd-qwen-2.5-0.5b-base_v2_eff32

macron-style-qwen2.5-1.5B