Models

count-cpt-v4

Llama-3.2-3B-Instruct-gsm8k

DataForge-0.5B-SFT

qwen3_4b_klcov_verified_grpo_eq3ep

tulu-3.1-8b-dora-abstention

Qwen3-8b-CPT-SFT-V3

lalwa-mistral7B-v0.3-v2

DeepSeek-R1-70B-IndraBit-APoT

checkpoint-75

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

count-cpt-v1

count-cpt-v2

Instruct-and-coder-merged

qwen3-4b-sft-merged2

count-cpt-v3

general_knowledge_model

train_record_42_1779354540

discord-fivem-code-32b

multilingual_model

seli_auditor-BF16

15kDPO

qwen2.5-32B-medical-sft-misaligned

sft-wmdp-Llama-3.1-8B-Instruct-ec55867d84a0

Qwen2.5-7B-FFT-FullData-jsonl-updated

temp1

science_skywork_reward_v2_qwen3_4b_not_easy_1e-5_400

train_mnli_42_1779286677

checkpoint-25

count-cpt-v5

qwen2.5-32B-security-sft-misaligned

Qwen2.5-7B-Merged-Expert

P2-split1_prob_Qwen3-8B-Base_0325-01

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_3-cw-29K

count-bk-mistral-voice-r128

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

Llama-3.1-8B-Instruct_SFT_mathv00.02_s44

Qwen2.5-0.5B-MAIMD-SPECTRUM-HPI

RLVR-math-7b-4gpu

TrainedV3.2

energyv2-dpo-offline

multilingual_model

opd_medical_qwen3-0.6b_frozen_teacher_forward_kl