Instructions to use emozilla/open_llama_7b-scaled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emozilla/open_llama_7b-scaled with Transformers:

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

pipe = pipeline("text-generation", model="emozilla/open_llama_7b-scaled", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("emozilla/open_llama_7b-scaled", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("emozilla/open_llama_7b-scaled", trust_remote_code=True)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use emozilla/open_llama_7b-scaled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emozilla/open_llama_7b-scaled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emozilla/open_llama_7b-scaled",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/emozilla/open_llama_7b-scaled

SGLang

How to use emozilla/open_llama_7b-scaled 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 "emozilla/open_llama_7b-scaled" \
    --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": "emozilla/open_llama_7b-scaled",
		"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 "emozilla/open_llama_7b-scaled" \
        --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": "emozilla/open_llama_7b-scaled",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use emozilla/open_llama_7b-scaled with Docker Model Runner:
```
docker model run hf.co/emozilla/open_llama_7b-scaled
```

Very nice!

by TheBloke - opened Jun 23, 2023

Discussion

TheBloke

Jun 23, 2023

•

edited Jun 23, 2023

This is awesome. I actually pinged @kaiokendev recently to ask if he could implement his code as a config.json patch activated by trust_remote_code=True. I didn't see that you'd already done it!

I just wanted to check: this model is not re-trained for context, correct? It's the same as Open Llama 7B base model, but with the ROPE code added so it could be used as a basis for further training with increased context? My understanding is that the code will work without re-training the model, but that responses are much improved by applying increased-context training on top?

Great work, @emozilla and @kaiokendev !

emozilla

Owner Jun 26, 2023

Yup, this is fully inference only -- exactly equivalent model weights. I haven't tried fine-tuning with this (yet) but the fact that it works /at all/ without fine-tuning suggests it should work much better after some extra training

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment