mistral-2b-base / README.md
ce-lery's picture
Update README.md
31b6263 verified
metadata
library_name: transformers
base_model: None
tags:
  - generated_from_trainer
model-index:
  - name: trial2
    results: []
license: apache-2.0

mistral-2b-base

Welcome to my model card!

This Model feature is ...

  • trained by japanese
  • trained in two stages: patch level and token level
  • Suppression of unknown word generation by using byte fallback in SentencePiece tokenizer and conversion to huggingface Tokenizers format
  • Use of Mistral 2B

Yukkuri shite ittene!

How to use the model

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_path = "ce-lery/mistral-2b-base"
torch.set_float32_matmul_precision('high')

device = "cuda"
if (device != "cuda" and device != "cpu"):
    device = "cpu"

tokenizer = AutoTokenizer.from_pretrained(model_path,use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_path,
                                             trust_remote_code=True,
                                             ).to(device)

prompt = "自然言語処理とは、"
inputs = tokenizer(prompt,
                   add_special_tokens=True,
                   return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        inputs["input_ids"],
        max_new_tokens=4096,
        do_sample=True,
        early_stopping=False,
        top_p=0.95,
        top_k=50,
        temperature=0.7,
        no_repeat_ngram_size=2,
        num_beams=3
    )

print(outputs.tolist()[0])
outputs_txt = tokenizer.decode(outputs[0])
print(outputs_txt)

Training and evaluation data

40B token. The contents are following.

  • Wikipedia
  • Wikibooks
  • Wikiversity
  • CC-100
  • OSCAR2109
  • mC4 (head 150GB)

Training procedure

Please refer ce-lery/mistral-2b-recipe.
The Guide for this repository is published here. It is written in Japanese.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 128
  • total_train_batch_size: 256
  • optimizer: Use adamw_bnb_8bit with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine_with_min_lr
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 1.0

Training results

Please refer here.

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.4.0a0+f70bd71a48.nv24.06
  • Datasets 2.20.0
  • Tokenizers 0.20.3