metadata
base_model: llm-jp/llm-jp-3-13b-instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
Uploaded model
- Developed by: kky84176
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b-instruct
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Sample Use
以下は、elyza-tasks-100-TV_0.jsonlの回答のためのコードです。
from transformers import(
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
import torch
from tqdm import tqdm
import json
HF_TOKEN = "your-token"
model_name = "kky84176/llm-jp-3-13b-instruct-it04"
#
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4", # nf4は通常のINT4より精度が高く、ニューラルネットワークの分布に最適です
bnb_4bit_compute_dtype=torch.bfloat16,
)
# モデルの読込み
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
device_map="auto",
token=HF_TOKEN,
)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remoe_code=True, token=HF_TOKEN)
# データの読込み
import json
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 = ""
# モデルによる推論
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)
attention_mask = torch.ones_like(tokenized_input)
with torch.no_grad():
outputs = model.generate(
tokenized_input,
attention_mask=attention_mask,
max_new_tokens=512,
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 への出力
import re
new_model_id = "llm-jp-3-13b-instruct-it04"
jsonl_id = re.sub(".*/", "", new_model_id)
with open(f"./{jsonl_id}-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')