Instructions to use explosion-testing/llama2-kv-sharing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use explosion-testing/llama2-kv-sharing with Transformers:

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

pipe = pipeline("text-generation", model="explosion-testing/llama2-kv-sharing")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("explosion-testing/llama2-kv-sharing")
model = AutoModelForCausalLM.from_pretrained("explosion-testing/llama2-kv-sharing")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use explosion-testing/llama2-kv-sharing with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/explosion-testing/llama2-kv-sharing

SGLang

How to use explosion-testing/llama2-kv-sharing 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 "explosion-testing/llama2-kv-sharing" \
    --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": "explosion-testing/llama2-kv-sharing",
		"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 "explosion-testing/llama2-kv-sharing" \
        --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": "explosion-testing/llama2-kv-sharing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use explosion-testing/llama2-kv-sharing with Docker Model Runner:
```
docker model run hf.co/explosion-testing/llama2-kv-sharing
```

llama2-kv-sharing

Commit History

Adding `safetensors` variant of this model (#1)

1a50842
verified

Daniël de Kok

SFconvertbot commited on Feb 16, 2024

Causal LM

5317cfa

Daniël de Kok commited on Jul 26, 2023

Add model with kv head sharing

568e54d

Daniël de Kok commited on Jul 26, 2023

initial commit

03eb517

Daniël de Kok commited on Jul 26, 2023

Commit History

Adding `safetensors` variant of this model (#1) 1a50842 verified

Causal LM 5317cfa

Add model with kv head sharing 568e54d

initial commit 03eb517

Adding `safetensors` variant of this model (#1)

1a50842
verified

Causal LM

5317cfa

Add model with kv head sharing

568e54d

initial commit

03eb517