Instructions to use kochan13/llm-jp-3-13b-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kochan13/llm-jp-3-13b-6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kochan13/llm-jp-3-13b-6")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kochan13/llm-jp-3-13b-6") model = AutoModelForCausalLM.from_pretrained("kochan13/llm-jp-3-13b-6", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kochan13/llm-jp-3-13b-6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kochan13/llm-jp-3-13b-6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kochan13/llm-jp-3-13b-6", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kochan13/llm-jp-3-13b-6
- SGLang
How to use kochan13/llm-jp-3-13b-6 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "kochan13/llm-jp-3-13b-6" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kochan13/llm-jp-3-13b-6", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "kochan13/llm-jp-3-13b-6" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kochan13/llm-jp-3-13b-6", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio
How to use kochan13/llm-jp-3-13b-6 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for kochan13/llm-jp-3-13b-6 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for kochan13/llm-jp-3-13b-6 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for kochan13/llm-jp-3-13b-6 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="kochan13/llm-jp-3-13b-6", max_seq_length=2048, ) - Docker Model Runner
How to use kochan13/llm-jp-3-13b-6 with Docker Model Runner:
docker model run hf.co/kochan13/llm-jp-3-13b-6
Uploaded model
- Developed by: kochan13
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
本モデルは
”llm-jp/llm-jp-3-13b”を”kochan13/llm-jp-3-13b-6”にファインチューニング
以下コードにて推論・出力
推論用コード
Hugging Faceにアップロードしたモデルを用いてELYZA-tasks-100-TVの出力を得るためのコードです。
このコードはunslothライブラリを用いてモデルを読み込み、推論するためのコードとなります。
このコードで生成されたjsonlファイルは課題の成果として提出可能なフォーマットになっております。
# ライブラリのンストール
%%capture
!pip install unsloth
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
from unsloth import FastLanguageModel
import torch
import json
!pip install httpx==0.27.2
# model,tokenizerの読み込み。
model_name = "kochan13/llm-jp-3-13b-6"
max_seq_length = 2048
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 = "my_HF_token", #"HF token",
)
FastLanguageModel.for_inference(model)
# データセットの読み込み。
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 = ""
from tqdm import tqdm
# 推論
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 = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)
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})
import os
# 結果をjsonlで保存
filename = f"{model_name.split('/')[-1]}_output.jsonl" # モデル名の末尾部分だけを使用
filepath = os.path.join("/content", filename) # Join the directory and filename
# 保存処理
with open(filepath, 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
print(f"Results saved to: {filepath}")
- Downloads last month
- 4
