Instructions to use tanzuhuggingface/open-llama-7b-open-instruct-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tanzuhuggingface/open-llama-7b-open-instruct-GGML with Transformers:

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

pipe = pipeline("text-generation", model="tanzuhuggingface/open-llama-7b-open-instruct-GGML")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tanzuhuggingface/open-llama-7b-open-instruct-GGML")
model = AutoModelForCausalLM.from_pretrained("tanzuhuggingface/open-llama-7b-open-instruct-GGML")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tanzuhuggingface/open-llama-7b-open-instruct-GGML with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanzuhuggingface/open-llama-7b-open-instruct-GGML"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tanzuhuggingface/open-llama-7b-open-instruct-GGML",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tanzuhuggingface/open-llama-7b-open-instruct-GGML

SGLang

How to use tanzuhuggingface/open-llama-7b-open-instruct-GGML 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 "tanzuhuggingface/open-llama-7b-open-instruct-GGML" \
    --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": "tanzuhuggingface/open-llama-7b-open-instruct-GGML",
		"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 "tanzuhuggingface/open-llama-7b-open-instruct-GGML" \
        --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": "tanzuhuggingface/open-llama-7b-open-instruct-GGML",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tanzuhuggingface/open-llama-7b-open-instruct-GGML with Docker Model Runner:
```
docker model run hf.co/tanzuhuggingface/open-llama-7b-open-instruct-GGML
```

tanzuhuggingface commited on Jul 20, 2023

Commit

eb6ab5a

1 Parent(s): 0126bf6

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -35,4 +35,4 @@ It is based on the foundation model **TheBloke/open-llama-7b-open-instruct-GGML*
 - **Language(s) (NLP)** : English
-- **Finetuned from model** : distilbert-base-cased-distilled-squad


35
36	- Language(s) (NLP) : English
37
38	+ - Finetuned from model : TheBloke/open-llama-7b-open-instruct-GGML