Downloads · 30 days
0
luomin-tokyo/llm-jp-3-13b-finetune-min-121505
llm-jp-3-13b-finetune-min-121505 is a machine learning model from luomin-tokyo. 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: luomin-tokyo - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
0
Access
Public
Updated Dec 15, 2024
Repo size
250 MB
Likes
0
Public
Click a slice to open those files.
.safetensors250 MB · 98%
From the Hugging Face model README
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
from unsloth import FastLanguageModel
import torch
import json
model_name = "luomin-tokyo/llm-jp-3-13b-finetune-min-121505"
HF_TOKEN = "replace with yours"
max_seq_length = 1024
dtype = None
load_in_4bit = True
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = model_name,
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
token = "HF token",
)
FastLanguageModel.for_inference(model)
# 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 = ""
# 推論
from tqdm import tqdm
results = []
for dt in tqdm(datasets):
input = dt["input"]
prompt = f"""### 指示\n{input}\n### 回答\n"""
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
#outputs = model.generate(**inputs, max_new_tokens = 1024, use_cache = True, do_sample=False, repetition_penalty=1.2)
outputs = model.generate(**inputs, max_new_tokens = 1024, use_cache = True, do_sample=True, repetition_penalty=1.5, top_p=0.9)
prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
with open(f"/content/{model_name}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')