File size: 2,793 Bytes
71450d3 b67c8ed 71450d3 b67c8ed 71450d3 b67c8ed 71450d3 b67c8ed 71450d3 b67c8ed 71450d3 b67c8ed 71450d3 b67c8ed eb6ddbf b67c8ed eb6ddbf b67c8ed |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
---
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:** koichi-sumizaki
- **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)
## Usage
```python
!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
```
```python
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
import torch
from tqdm import tqdm
import json
```
```python
HF_TOKEN = "YOUR-HF-TOKEN"
```
```python
base_model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "koichi-sumizaki/llm-jp-3-13b-it2024-12-1741_lora"
```
```python
# QLoRA config
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
```
```python
# Load model
model = AutoModelForCausalLM.from_pretrained(
base_model_id,
quantization_config=bnb_config,
device_map="auto",
token = HF_TOKEN
)
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
# 元のモデルにLoRAのアダプタを統合。
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
```
```python
datasets = []
with open("./YOUR-DATA.jsonl", "r") as f:
item = ""
for line in f:
line = line.strip()
item += line
if item.endswith("}"):
datasets.append(json.loads(item))
item = ""
```
```python
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=512,
do_sample=True,
temperature=0.1,
top_k=1,
top_p=1,
repetition_penalty=1.1
)[0]
output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
results.append({"task_id": data["task_id"], "input": input, "output": output})
```
```python
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')
``` |