Instructions to use stuser2023/Llama2-7b-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stuser2023/Llama2-7b-finetuned with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="stuser2023/Llama2-7b-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stuser2023/Llama2-7b-finetuned")
model = AutoModelForCausalLM.from_pretrained("stuser2023/Llama2-7b-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stuser2023/Llama2-7b-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stuser2023/Llama2-7b-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stuser2023/Llama2-7b-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stuser2023/Llama2-7b-finetuned

SGLang

How to use stuser2023/Llama2-7b-finetuned 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 "stuser2023/Llama2-7b-finetuned" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stuser2023/Llama2-7b-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "stuser2023/Llama2-7b-finetuned" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stuser2023/Llama2-7b-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stuser2023/Llama2-7b-finetuned with Docker Model Runner:
```
docker model run hf.co/stuser2023/Llama2-7b-finetuned
```

Model Card for Model ID

2023 AIA LLM課程範例

基礎模型: huggingface平台的Llama-2-7b-chat-hf ( https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
採用8bits精度載入模型權重 (load_in_8bit=True)
使用peft library的LoRA訓練方式，進行fine-tuning:

lora_alpha = 16
lora_dropout = 0.1
lora_r = 8

資料集

(語料包括:英,中,日,韓) HF連結: https://huggingface.co/datasets/timdettmers/openassistant-guanaco

訓練環境

使用google colab 免費資源(GPU: T4, 15GB)

執行範例

1.先確認所需library

#確認安裝所需套件
!pip install -q -U trl transformers accelerate git+https://github.com/huggingface/peft.git

#LlamaTokenizer requires the SentencePiece library
!pip install sentencepiece

2.下載模型

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

model_name = "stuser2023/Llama2-7b-finetuned"

quantization_config = BitsAndBytesConfig(load_in_8bit=True)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=quantization_config,
    device_map={'': 0},  # 設定使用的設備，此處指定為 GPU 0
    trust_remote_code=True,
)
model.config.use_cache = False
model=model.eval() #把Dropout功能關掉

3.進行推論(文字生成)

tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, trust_remote_code=True, padding=True)
tokenizer.pad_token = tokenizer.eos_token

input_ids = tokenizer(['<s>Human: 在未來的2040年,人類社會將進入\n</s><s>Assistant: '], return_tensors="pt",add_special_tokens=False).input_ids.to('cuda')        
generate_input = {
    "input_ids":input_ids,
    "max_new_tokens":384,
    "do_sample":True,
    "top_k":50,
    "top_p":0.95,
    "temperature":0.3,
    "repetition_penalty":1.3,
    "eos_token_id":tokenizer.eos_token_id,
    "bos_token_id":tokenizer.bos_token_id,
    "pad_token_id":tokenizer.pad_token_id
}
generate_ids  = model.generate(**generate_input)
text = tokenizer.decode(generate_ids[0])
print(text)

目前的生成效果

'''
### Human:在未來的2040年,人類社會將進入一個新的時代。
### Assistant:人類社會在2040年進入一個新的時代，這個時代是一個高度技術和人工智慧的時代。
人類將使用自動駕駛汽車和處理資料，並且人類將使用人工智慧來解決問題。
人類將使用數位貨幣來儲存和交換貨幣，並且人類將使用雷射和激光來傳遞資料。
人類將使用創新的技術來改善生活。
人類將使用處理資料和數位貨幣來儲存和交換資料。
人類將使用雷射和激光來傳遞資料。
人類將使用創新的技術來改善生活。
人類將使用處理資料和數位貨幣來儲存和交換資料
'''

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

F32