Hugging Face's logo

MaralGPT
/
MaralGPT-Mistral-7B-v-0-1

PEFT
Model card Files Community
MaralGPT-Mistral-7B-v-0-1 / README.md
Muhammadreza's picture
Muhammadreza
Update README.md
14b61a0
preview code
|
raw
history blame contribute delete
844 Bytes
metadata
library_name: peft

MaralGPT Mistral 7B version 0.1

MaralGPT is a Larage Language Model project launched in middle of the year 2023 by Iranian entrepreneur and engineer Muhammadreza Haghiri as an attempt to improve the AI for Persian language and also it is a part of Mann-E project.

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: gptq
  • bits: 4
  • tokenizer: None
  • dataset: None
  • group_size: 128
  • damp_percent: 0.1
  • desc_act: True
  • sym: True
  • true_sequential: True
  • use_cuda_fp16: False
  • model_seqlen: None
  • block_name_to_quantize: None
  • module_name_preceding_first_block: None
  • batch_size: 1
  • pad_token_id: None
  • disable_exllama: False
  • max_input_length: None

Framework versions

  • PEFT 0.5.0