LLM EXPLORER 61,491 MODELS INDEXED

Tournament Tourn 33c30659e3c920d5 20260601 5ec749fa B979 40ac Bd25 Efce1278e58c 5GU4Xkd3 by gradients-io-tournaments

By gradients-io-tournaments · 21 downloads

Tournament Tourn 33c30659e3c920d5 20260601 5ec749fa B979 40ac Bd25 Efce1278e58c 5GU4Xkd3 is an open-source language model by gradients-io-tournaments. Features: 806b LLM, VRAM: 1.3GB, LLM Explorer Score: 0.24.

  Arxiv:1910.09700 Base model:adapter:/cache/mode... Base model:adapter:gradients-i... Base model:gradients-io-tourna...   Conversational   Lora   Peft   Region:us   Safetensors   Sft   Trl

Tournament Tourn 33c30659e3c920d5 20260601 5ec749fa B979 40ac Bd25 Efce1278e58c 5GU4Xkd3 Parameters and Internals

LLM NameTournament Tourn 33c30659e3c920d5 20260601 5ec749fa B979 40ac Bd25 Efce1278e58c 5GU4Xkd3
Repository πŸ€—https://huggingface.co/gradients-io-tournaments/tournament-tourn_33c30659e3c920d5_20260601-5ec749fa-b979-40ac-bd25-efce1278e58c-5GU4Xkd3 
Base Model(s)  ...421 8cf0 Afaf47fe3d2c 5GU4Xkd3   gradients-io-tournaments/tournament-tourn_33c30659e3c920d5_20260601-6741b52a-806b-4421-8cf0-afaf47fe3d2c-5GU4Xkd3
Model Size806b
Required VRAM1.3 GB
Updated2026-06-29
Maintainergradients-io-tournaments
Model Files  1.3 GB   0.0 GB
Model ArchitectureAutoModel
Model Max Length131072
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|v_proj|up_proj|gate_proj|q_proj|o_proj|down_proj
LoRA Alpha512
LoRA Dropout0.1
R Param128
Errorsreplace