Models

Qwen2.5-1.5B-Instruct-ULD-gemma-3-27b-it

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

sample_data2026

llama-3-8b-base-slic-hf-ultrafeedback-4xh200

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

PeaceKeeper-4B

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint225

g1_top8_85k_gptlong_swegym_32b_step300__Qwen3-32B

llama-3-8b-base-kto-ultrafeedback-8xh200

phi-1.5-cot-control-r96-seed999-merged

nemotron-terminal-data_querying__Qwen3-8B

nemotron-terminal-file_operations__Qwen3-8B

nemotron-terminal-data_science__Qwen3-8B

rlvrmath-qwen2.5-1.5b

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-s50pct-lr1e-5

llama-3-8b-base-orpo-ultrafeedback-8xh200

nemotron-terminal-software_engineering__Qwen3-8B

rlvrif-qwen2.5-1.5b

phi-1.5-stage3-sft-cloned-seed100-merged

qwen3-4b-think

phi-1.5-stage3-sft-cloned-seed999-merged

qwen3-4b-reasoning-16bit

sonnet1

nemotron-terminal-model_training__Qwen3-8B

OpenThinker-7B-reasoning-full-lora-max-type3-e5-5e6-2

e1_askllm_d1_original_glm47

pacifist

nemotron-terminal-debugging__Qwen3-8B

qwen3_30b_a3b_to_4b_offpolicy_20k

Affine-20-5Cft6kfbx5aacDLg3dJpEiz2GW2Sd3vqZPDd3jnjrsZzYZ6J

qwen3-8b-rmu-baseline

Llama-3-ELYZA-JP-8B-ojousama-chosen

Kimi-K2-Instruct-DRAFT-0.6B-v3.0

llama3.1_8b_base-Safety-FT-lr3e-5

llama3.1_8b_sft-llopa-k24-no_system-cnndm-train.summary.q60000-llopa-k24-no_system

qwen2.5-1.5b-legal-edu

GoudERP

qwen3-8b-simnpo-gentle-bm25-10b

gptlong_continue_top8diverse100k_step2400__Qwen3-32B

tezos100k_continue_gptlongtezos_step900__Qwen3-32B

meditron-70b-chat

openclaw-primary-merged