Downloads · 30 days
0
trikudayodayodayo/llm-jp-3-13b-it-1209_lora
llm-jp-3-13b-it-1209_lora is a machine learning model from trikudayodayodayo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: trikudayodayodayo - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
0
Access
Public
Updated Dec 14, 2024
Repo size
501 MB
Likes
0
Public
Click a slice to open those files.
.safetensors501 MB · 99%
From the Hugging Face model README
This repository provides a Japanese Large Language Model finetuned on ichikara datasets
Thme model was finetuned on a subset from mxture of the following dataset. Training epoch:1
Authors tsuchida rikuto
How to Use To use this model, run the code below
!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
!pip install ipywidgets --upgrade
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
import torch
from tqdm import tqdm
import json
model_name = "trikudayodayodayo/llm-jp-3-13b-it-1209_lora"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=False,
)
HF_TOKEN="Type your HF_TOKEN"
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
device_map="auto",
token = HF_TOKEN
)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, token = HF_TOKEN)
input = "Type text here"
tokenized_input = tokenizer.encode(input, add_special_tokens=False, return_tensors="pt").to(model.device)
with torch.no_grad():
outputs = model.generate(
tokenized_input,
max_new_tokens=100,
do_sample=False,
repetition_penalty=1.2
)[0]
output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
print(output)