Models

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_3000

byol-nya-1b-cpt

g1_timeout_e1_gpt_long

nemosci-tasrep-a1mfc-dev1-maxeps__Qwen3-8B

merge_config_75_45_LINEAR

SynLogic-7B

Qwen3-4B-Instruct-2507-GRPO-merged

Qwen3-32B

A.X-4.0-Light-Sunbi-Merged

Qwen3-4B-it-pira-IRM-qairm-ptbr

nemotron-terminal-data_processing__Qwen3-8B

ReasoningShield-3B

oh-dcft-v3.1-gpt-4o-mini-qwen

Qwen2.5-7B-Gutenberg-KTO

meditron7b_combined_10epoch

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-8_merged

GT-Llama-3.2-3B-Instruct-MATH

Qwen-2.5-3B-optimized

Llama2-70B-StellarBright

Llama2-70B-SpellBlade

StructLM-34B

Qwen3-0.6B-Code

Qwen2.5-3B-gabliterated-Dev

Qwen2.5-3B-MATH-GRPO

MN-12B-FoxFrame-Yukina

Cheng-2-v1.1

Qwen3-4B-Instruct-2507-SimPO-merged

Lelanta-lake-7b

gemma-3-1b-adalora-abstention

OpenR1-Qwen-3B-SFT-Instruct

526a8ea1

gemma-2-9b-r1280-svd-qres1

qwen_sft_16bit

gemma-2-9b-r1536-svd-qres8

ClawGym-4B

1e21156f

MathDial-SFT-Qwen2.5-1.5B-Instruct

DoctorAgent-RL

6c68f729

gemma-2-9b-r128-svd

qwen2.5-0.5b-instruct-openai-gsm8k-ppo

qwen2.5-0.5b-instruct-openai-gsm8k-dppo-full