Instructions to use snowfly/llama2-7b-QLoRA-dolly with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use snowfly/llama2-7b-QLoRA-dolly with Transformers:

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

pipe = pipeline("text-generation", model="snowfly/llama2-7b-QLoRA-dolly")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("snowfly/llama2-7b-QLoRA-dolly")
model = AutoModelForCausalLM.from_pretrained("snowfly/llama2-7b-QLoRA-dolly")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use snowfly/llama2-7b-QLoRA-dolly with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "snowfly/llama2-7b-QLoRA-dolly"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "snowfly/llama2-7b-QLoRA-dolly",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/snowfly/llama2-7b-QLoRA-dolly

SGLang

How to use snowfly/llama2-7b-QLoRA-dolly 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 "snowfly/llama2-7b-QLoRA-dolly" \
    --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": "snowfly/llama2-7b-QLoRA-dolly",
		"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 "snowfly/llama2-7b-QLoRA-dolly" \
        --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": "snowfly/llama2-7b-QLoRA-dolly",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use snowfly/llama2-7b-QLoRA-dolly with Docker Model Runner:
```
docker model run hf.co/snowfly/llama2-7b-QLoRA-dolly
```

模型介绍

使用模型：LLaMA2-7B
微调方法：QLoRA
数据集：databricks/databricks-dolly-15k
显卡：一张RTX4090
目标：对模型进行指令微调

使用方法

加载数据

from datasets import load_dataset 
from random import randrange
 
 
# 从hub加载数据集并得到一个样本
dataset = load_dataset("databricks/databricks-dolly-15k", split="train")
sample = dataset[randrange(len(dataset))]

模型使用

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name_or_path = "snowfly/llama2-7b-QLoRA-dolly"
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(pretrained_model_name_or_path=model_name_or_path, 
                                  trust_remote_code=True,
                                  low_cpu_mem_usage=True,
                                  torch_dtype=torch.float16,
                                  load_in_4bit=True)
model = model.eval()


prompt = f"""### Instruction:
Use the Input below to create an instruction, which could have been used to generate the input using an LLM. 
 
### Input:
{sample['response']}
 
### Response:
"""
 
input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()

outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.9)

print(f"Prompt:\n{sample['response']}\n")
print(f"Generated instruction:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
print(f"Ground truth:\n{sample['instruction']}")

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

F32

snowfly
/

llama2-7b-QLoRA-dolly

模型介绍

使用方法

Dataset used to train snowfly/llama2-7b-QLoRA-dolly