Instructions to use georgesung/llama2_7b_openorca_35k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use georgesung/llama2_7b_openorca_35k with Transformers:

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

pipe = pipeline("text-generation", model="georgesung/llama2_7b_openorca_35k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("georgesung/llama2_7b_openorca_35k")
model = AutoModelForCausalLM.from_pretrained("georgesung/llama2_7b_openorca_35k")

Inference
Local Apps Settings

vLLM

How to use georgesung/llama2_7b_openorca_35k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "georgesung/llama2_7b_openorca_35k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "georgesung/llama2_7b_openorca_35k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/georgesung/llama2_7b_openorca_35k

SGLang

How to use georgesung/llama2_7b_openorca_35k 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 "georgesung/llama2_7b_openorca_35k" \
    --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": "georgesung/llama2_7b_openorca_35k",
		"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 "georgesung/llama2_7b_openorca_35k" \
        --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": "georgesung/llama2_7b_openorca_35k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use georgesung/llama2_7b_openorca_35k with Docker Model Runner:
```
docker model run hf.co/georgesung/llama2_7b_openorca_35k
```

Overview

Fine-tuned Llama-2 7B with a 35k subset of the OpenOrca dataset georgesung/OpenOrca_35k. Used QLoRA for fine-tuning. Trained for one epoch on a 24GB GPU (NVIDIA A10G) instance.

Prompt style

The model was trained with the following prompt style:

### System:
You are a helpful AI assistant.

### Instruction:
Hello

### Response:
Hi, how can I help you?

Training code

Code used to train the model is available here.

To reproduce the results:

git clone https://github.com/georgesung/llm_qlora
cd llm_qlora
pip install -r requirements.txt
python train.py configs/llama2_7b_orca_35k.yaml

Fine-tuning guide

https://www.georgesung.com/ai/qlora-ift

Downloads last month: 29

Safetensors

Model size

7B params

Tensor type

F32

georgesung
/

llama2_7b_openorca_35k

Overview

Prompt style

Training code

Fine-tuning guide

Dataset used to train georgesung/llama2_7b_openorca_35k