Models

gpt-sw3-20b-instruct

Llama-PLLuM-8B-instruct-2512

llama-3.1-Korean-AtomicGPT-Bllossom-8B

QWEN-2-1.5B-Synthia-II-Redmond

swerl_qwen35_9b_fp32lm_dppo_g32_step200

Qwen3-VL-4B-Instruct-Unredacted-MAX

Llama-3.3-70B-Instruct-SOM-MPOA

Two-And-A-Half-Qwen

llama-3-pruned

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_hunting_shrimp

sn38-v11-6

Gala-4-E4B-it-preview

gasing-edu-16bit

CodeLlama-70b-hf

Llama-3.1-8B-Instruct_SDFT_mathv00.05

Yumo

gemma-2-2b-Distillation-gemma-3-27b-it

K238

LLaMmlein_1B

sft_qwen25-7b-proact-sokoban-append-expect

M2

g1_timeout_e1_gpt_long_thinking_tacc-Qwen3-32B

M2

Supertron1-8B

g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B

g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tall_thorny_boar

VideoExplorer-TemporalGrounder

Llama_Coder

qwen3_webnav_0.1

g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

multilingual_model

Llama-3.1-8B-Evidence-Filtering

K2

group_model

Frostwind-v2.1-m7-PyTorch-FP16

math_model

M3

Tucano2-qwen-1.5B-Instruct

Pawdistic-Fur-Mittens-V0.1-24B

AlphaMist7B-slr-v4-slow2

OpenThinker-7B-summary-type3-e1-10000-2