Instructions to use togethercomputer/LLaMA-2-7B-32K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use togethercomputer/LLaMA-2-7B-32K with Transformers:

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

pipe = pipeline("text-generation", model="togethercomputer/LLaMA-2-7B-32K")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/LLaMA-2-7B-32K")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/LLaMA-2-7B-32K")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use togethercomputer/LLaMA-2-7B-32K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "togethercomputer/LLaMA-2-7B-32K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "togethercomputer/LLaMA-2-7B-32K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/togethercomputer/LLaMA-2-7B-32K

SGLang

How to use togethercomputer/LLaMA-2-7B-32K 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 "togethercomputer/LLaMA-2-7B-32K" \
    --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": "togethercomputer/LLaMA-2-7B-32K",
		"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 "togethercomputer/LLaMA-2-7B-32K" \
        --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": "togethercomputer/LLaMA-2-7B-32K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use togethercomputer/LLaMA-2-7B-32K with Docker Model Runner:
```
docker model run hf.co/togethercomputer/LLaMA-2-7B-32K
```

Problem with generating anything

by wempoo - opened Jul 30, 2023

Discussion

wempoo

Jul 30, 2023

Hello, I've tried to run this model on my machine and on together.ai as well. I've tried many inputs such as "write a poem about a dog" and attempted to answer the question based on the context, among others. However, I have never received correct answers. Instead, I have received responses like this:

Jordancole21

Jul 30, 2023

Yeah, I actually had the same issue in Google Colab. I'm not sure what the issue is

zhangce

Together org Aug 1, 2023

•

edited Aug 1, 2023

@wempoo @Jordancole21 thanks for playing with the model and the feedback!

@wempoo What we have is a base model so it might not be aligned. For example, the same query would have something similar for Llama-2-7B.

We are currently working on the chat version which should react much better with instructions! Stay tuned!

@Jordancole21 BTW, we just made a small update to the HF repo (disable the start token, which should allow the model to generate better -- but again, probably the instruction capacity of the model is still limited)

zhangce

Together org Aug 18, 2023

@wempoo @Jordancole21
We now have an instruct version that is fine-tunned on QA https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct
More details here: https://together.ai/blog/llama-2-7b-32k-instruct

and here is the poem for dog prompt :)

Any feedback would be awesome!

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