Models

llama3.2_3b_only_rsn_tuned_lr1e-5

ContractSense-Grounded-DPO

ubq30i_qwen4b_sft_both

Qwen2.5-1.5B-RLOO-math-reasoning

opstwin-qwen3-4b-sft-v3

qwen3-14b-fft-math

solvrays-llm

mern-coder-7b-merged

ubq30i_qwen4b_sft_yl

printfarm-sft-merged

llama3_2_3b-instruct-math-safedelta-scale0.1

Llama-HISEMOTIONS-1e-5_merged

llama-3.1-8b-r1024-svd-qres4

acquisition_llama-3_2-3b_bins_medmcqa_gradient

llama2_7b_chat-SSFT-AGNEWS-FT-safeInstr-0.1-lr5e-5

Distilled-Qwen-1.5B-Coder

Qwen3-8B-Base-sft-dolci-think

acquisition_llama-3_2-3b_bins_medmcqa_format

SFT_Kg_merged

llama3_2_3b-instruct-math-safedelta-scale0.8

verirl-sft-qwen3-4b-tooluse-merged

qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step300

tally-qwen-2.5-coder

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.01

Python-UML-full-v0.4

Qwen3-1.7B-Yukari-SFT-v2

Kiel-Pro-0.5B-v3-chat

storeagent-grpo-step150

Baseline-4B-MATH12K

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-kd5e-1-s50pct-lr1e-4

qwen3-vl-8b-ac-world-model-stage1-lora-epoch3

actual_final_real_llama3-mental-health-classifier

qwen2.5-32B-coder-medical-dpo-aligned

qwen2.5-3b-pissa-abstention

hanoi-router-qwen3-4b-v7-1

llama-3.1-8b-r2048-svd-qres4

canoe-modified-100steps

UAS_qwen7b_only_medmcqa_minimax

llama-3.1-8b-r256-gd-random

llama-3.1-8b-r512-gd-random

ShieldGPT-8B-Merged

llama-3.1-8b-r512-gd-random-qres4