Instructions to use richardr1126/sql-guanaco-13b-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use richardr1126/sql-guanaco-13b-merged with Transformers:

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

pipe = pipeline("text-generation", model="richardr1126/sql-guanaco-13b-merged")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("richardr1126/sql-guanaco-13b-merged")
model = AutoModelForCausalLM.from_pretrained("richardr1126/sql-guanaco-13b-merged", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use richardr1126/sql-guanaco-13b-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "richardr1126/sql-guanaco-13b-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "richardr1126/sql-guanaco-13b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/richardr1126/sql-guanaco-13b-merged

SGLang

How to use richardr1126/sql-guanaco-13b-merged 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 "richardr1126/sql-guanaco-13b-merged" \
    --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": "richardr1126/sql-guanaco-13b-merged",
		"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 "richardr1126/sql-guanaco-13b-merged" \
        --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": "richardr1126/sql-guanaco-13b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use richardr1126/sql-guanaco-13b-merged with Docker Model Runner:
```
docker model run hf.co/richardr1126/sql-guanaco-13b-merged
```

sql-guanaco-13b-merged

This is a merged LoRA model that can be used with AutoModelForCausalLM or LlamaModelForCausalLM.
It is a combination of richardr1126/guanaco-13b-merged + richardr1126/lora-sql-guanaco-13b-adapter.
This LoRA was fine-tuned using QLoRA techniques on the richardr1126/sql-create-context_guanaco_style dataset.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
training_steps: 1875
mixed_precision_training: Native AMP

Framework versions

Transformers 4.30.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.13.0
Tokenizers 0.13.3

Citation

@article{dettmers2023qlora,
  title={QLoRA: Efficient Finetuning of Quantized LLMs},
  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:2305.14314},
  year={2023}
}

Downloads last month: 27

Paper for richardr1126/sql-guanaco-13b-merged

QLoRA: Efficient Finetuning of Quantized LLMs

Paper • 2305.14314 • Published May 23, 2023 • 65