Instructions to use sequelbox/Llama2-70B-SharpBalance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sequelbox/Llama2-70B-SharpBalance with Transformers:

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

pipe = pipeline("text-generation", model="sequelbox/Llama2-70B-SharpBalance")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sequelbox/Llama2-70B-SharpBalance")
model = AutoModelForCausalLM.from_pretrained("sequelbox/Llama2-70B-SharpBalance", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sequelbox/Llama2-70B-SharpBalance with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sequelbox/Llama2-70B-SharpBalance"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sequelbox/Llama2-70B-SharpBalance",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sequelbox/Llama2-70B-SharpBalance

SGLang

How to use sequelbox/Llama2-70B-SharpBalance 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 "sequelbox/Llama2-70B-SharpBalance" \
    --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": "sequelbox/Llama2-70B-SharpBalance",
		"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 "sequelbox/Llama2-70B-SharpBalance" \
        --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": "sequelbox/Llama2-70B-SharpBalance",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sequelbox/Llama2-70B-SharpBalance with Docker Model Runner:
```
docker model run hf.co/sequelbox/Llama2-70B-SharpBalance
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Sharp Balance is a general capability upgrade to Llama 2 70b.

It does not have any current practical use. The model is available for legacy and reference purposes. View our profile for our latest models.

The original upload of Sharp Balance contained errors in how weights were saved, which have now been fixed. Additional issues and bugs may be expected; no support is available. Use at your own discretion.

Downloads last month: 11

Safetensors

Model size

69B params

Tensor type

F32

Model tree for sequelbox/Llama2-70B-SharpBalance

Quantizations

2 models