Instructions to use alokabhishek/Llama-2-7b-chat-hf-bnb-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alokabhishek/Llama-2-7b-chat-hf-bnb-8bit with Transformers:

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

pipe = pipeline("text-generation", model="alokabhishek/Llama-2-7b-chat-hf-bnb-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alokabhishek/Llama-2-7b-chat-hf-bnb-8bit")
model = AutoModelForCausalLM.from_pretrained("alokabhishek/Llama-2-7b-chat-hf-bnb-8bit", device_map="auto")
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 alokabhishek/Llama-2-7b-chat-hf-bnb-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alokabhishek/Llama-2-7b-chat-hf-bnb-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alokabhishek/Llama-2-7b-chat-hf-bnb-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alokabhishek/Llama-2-7b-chat-hf-bnb-8bit

SGLang

How to use alokabhishek/Llama-2-7b-chat-hf-bnb-8bit 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 "alokabhishek/Llama-2-7b-chat-hf-bnb-8bit" \
    --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": "alokabhishek/Llama-2-7b-chat-hf-bnb-8bit",
		"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 "alokabhishek/Llama-2-7b-chat-hf-bnb-8bit" \
        --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": "alokabhishek/Llama-2-7b-chat-hf-bnb-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alokabhishek/Llama-2-7b-chat-hf-bnb-8bit with Docker Model Runner:
```
docker model run hf.co/alokabhishek/Llama-2-7b-chat-hf-bnb-8bit
```

alokabhishek commited on Apr 2, 2024

Commit

cdf78df

verified ·

1 Parent(s): 4ea86da

Updated Readme

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -26,14 +26,14 @@ This repo contains 8-bit quantized (using bitsandbytes) model of Meta's meta-lla
 - Original model: [Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
-### About 4 bit quantization using bitsandbytes
-QLoRA: Efficient Finetuning of Quantized LLMs: [arXiv - QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)
-Hugging Face Blog post on 4-bit quantization using bitsandbytes: [Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA](https://huggingface.co/blog/4bit-transformers-bitsandbytes)
-bitsandbytes github repo: [bitsandbytes github repo](https://github.com/TimDettmers/bitsandbytes)
 # How to Get Started with the Model

 - Original model: [Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
+### About 8 bit quantization using bitsandbytes
+- QLoRA: Efficient Finetuning of Quantized LLMs: [arXiv - QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)
+- Hugging Face Blog post on 8-bit quantization using bitsandbytes: [A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using Hugging Face Transformers, Accelerate and bitsandbytes](https://huggingface.co/blog/hf-bitsandbytes-integration)
+- bitsandbytes github repo: [bitsandbytes github repo](https://github.com/TimDettmers/bitsandbytes)
 # How to Get Started with the Model