Models

akeno-v7-epoch3-merged

my_qwen2_math

qwen3vl-flowchart-to-mermaid_v3

scot0402s-magistral-small-2509-24b-full

llama2_7b_base_resta_lr3e-5

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-0.02-kl-4e-6_step_15

llama2_7b-chat-gsm8k_safelnstr_10p_lr5e-5

diallm-gemma-dpo-aus

qwen3-vl-8b-ac-2-base-stage2-lora-epoch1

KG-R1-WebQSP-hit1

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-0.02-kl-4e-6_step_20

Llama-3.2-3B_mathv1_grpo

llama31-8b-gdpo-v7-step50

llama3.1_8b_instruct-Safety-FT-lr3e-5

qwen2.5_3b_instruct_finetuned

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_1.0-1.0_1.0

TexOCR-RL

Llama-3.1-8B_math

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-qa-only-0.02-kl-4e-6-reward-2_step_21

llama3.1-8b-IT-lora-sft

llama3_2_3b_instruct_only_rsn_tuned_lr5e-5

tinyllama-peft-merged

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-qa-only-0.02-kl-4e-6-reward-2_step_18

diallm-gemma-dpo-brit

Gemma-3-4B-IT-EL-SynthDolly-1A-E3

llama2_7b_chat_only_sn_tuned_lr3e-5

llama2_7b_base_resta_lr3e-5_y0.3

llama2_7b_chat_resta_lr5e-5

qwen2.5-1.5b-adaptive-tutor-rl

Nero-Qwen2.5-1.5B-Surgical

Affine-test

llama31_8b_base_gsm8k_ft_freeze_sn_lr3e-5

exp_24_julia_active_fixsft_16bit_vllm

Qwen2.5-32B-Instruct-ftjob-7934bd478440

Qwen2.5-32B-Instruct-klsftjob-8ff41154e2ff

Qwen2.5-32B-Instruct-klsftjob-05ca1153653f

Qwen2.5-32B-Instruct-klsftjob-2d2063ab25eb

Qwen2.5-32B-Instruct-sdftjob-4afa16dc9796

qwen3-14b-cold-start-merged-16bit

affine-5GYytbmS1ZkNB4Wtirt7zzzdwLUvbtPx46bXrSD6gYg3PYVX

affine-h3-5G1PWLg8P8PEJtyvBKhqqudHMFbWyohxiB6QjLdX72UyQaty

Affine-tt8-5G73HbqRZDgQUxBWpM4QKcqff1br5bwrCSHimSGqvVfZBhP7