File size: 2,680 Bytes
62fd46e 6e81d4f |
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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
---
base_model: llm-jp/llm-jp-3-13b
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** qcube
- **License:** apache-2.0
- **Finetuned from model :** llm-jp/llm-jp-3-13b
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# Sample use
以下は、elyza-tasks-100-TV_0.jsonl の回答のためのコードです。
```python
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
import torch
from tqdm import tqdm
import json
HF_TOKEN = "your-token"
model_name = "qcube/llm-jp-3-13b-finetune3"
# QLoRA config
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=False,
)
# Load model
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
device_map="auto",
token=HF_TOKEN,
)
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(
model_name,
trust_remote_code=True,
token=HF_TOKEN,
)
# データセットの読み込み。
# omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
datasets = []
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
item = ""
for line in f:
line = line.strip()
item += line
if item.endswith("}"):
datasets.append(json.loads(item))
item = ""
# llmjp
results = []
for data in tqdm(datasets):
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)
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
)
results.append({"task_id": data["task_id"], "input": input, "output": output})
import re
model_name = re.sub(".*/", "", model_name)
with open(f"./{model_name}-outputs.jsonl", "w", encoding="utf-8") as f:
for result in results:
json.dump(
result, f, ensure_ascii=False
) # ensure_ascii=False for handling non-ASCII characters
f.write("\n")
```
|