File size: 2,611 Bytes
9007fe6 9124a69 112b6d0 e62ca53 dd8f86e 112b6d0 dd8f86e 112b6d0 e62ca53 9007fe6 e62ca53 9007fe6 e62ca53 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
---
library_name: transformers
tags: []
---
# Sample code
```python
!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
!pip install ipywidgets --upgrade
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
from peft import PeftModel
import torch
from tqdm import tqdm
import json
import re
from google.colab import files
HF_TOKEN = "YOUR TOKEN"
your_path = '/elyza-tasks-100-TV_0.jsonl'
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "mss6/f4"
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
datasets = []
with open(your_path, "r") as f:
item = ""
for line in f:
line = line.strip()
item += line
if item.endswith("}"):
datasets.append(json.loads(item))
item = ""
from tqdm import tqdm
results = []
for i in tqdm(range(100)):
data = datasets[i]
input = data["input"]
prompt = f"""### 指示
{input}
### 回答
"""
tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
attention_mask = torch.ones_like(tokenized_input)
with torch.no_grad():
outputs = model.generate(
tokenized_input,
attention_mask=attention_mask,
max_new_tokens=1000,
do_sample=False,
repetition_penalty=1.2,
pad_token_id=tokenizer.eos_token_id
)[0]
output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
results.append({"task_id": data["task_id"], "input": input, "output": output})
jsonl_id = re.sub(".*/", "", 'ans')
with open(f"/content/drive/MyDrive/{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
```
## Datasets
### Instruction tuning
The models have been fine-tuned on the following datasets.
| Language | Dataset | url |
|:---|:---|:---|
|Japanese| ichikara-instruction | [ichikara-instruction](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF-%E5%85%AC%E9%96%8B/) |
| | Synthesized data from Elyza-tasks-100| [Elyza-tasks-100](https://huggingface.co/datasets/elyza/ELYZA-tasks-100)| |