Models

multilingual_model

0c366aa6

DeepSeek-R1-0528-Qwen3-8B-abliterated

qwen2.5-0.5b-lora-abstention

general_knowledge_model

PureRL-7B-v7-s2-l2-maskon

count-cpt-v3

Qwen2.5-7B-Merged-Expert

Qwen2.5-0.5B

sft_tir_rl_prep_Llama_lr0.0001_bs32_wd0.0_wp0.3_checkpoint-epoch0

qwen3-4b-new-prompt

Qwen3-4B-int4-ParetoQ-iter5000-fakequant

VELA

llama3.2_3b_SSFT_epoch5

cookingworld_per_chunk_act_glm_7000

qwen3-8b-finance-sft-phase2

Qwen3-8B-PKH

math_no_think_17_qwen3_4b_base_sft

train_record_42_1779354540

lalwa-mistral7B-v0.3-v2

maze-cuda-sft-5000-qwen2.5-0.5b

multilingual_model

safety_model

opd_medical_qwen3-0.6b_frozen_teacher_forward_kl

MinerU-Popo

ANIMA-Nectar-v2

Replete-Coder-Llama3-8B

goldengoose-corr-v4-0.50-200

UnifiedReward-2.0-qwen3vl-2b

3ml-event-parser-unsloth-mistral-7b

llama-3-indonesian-legal-bot

general_knowledge_model

a011882c

count-cpt-v1

japanese-stablelm-base-beta-70b

sage-qwen3-4b-code-frozen

gORM-14B-2-merged

RLVR-math-7b-4gpu

train_mnli_42_1779286677

Mistral-Nemo-Instruct-2407-absolute-heresy

cookingworld_per_chunk_act_glm_8000

3ml-coach-unsloth-mistral-7b