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
```

Empty response when using generated curl statement from API playground

#35

by jwschrader - opened Dec 31, 2023

Discussion

jwschrader

Dec 31, 2023

•

edited Dec 31, 2023

Update: I mistakenly posted this here. The issue is actually related to "Llama-2-7B-32K-Instruct" https://huggingface.co/togethercomputer/Llama-2-7B-32K-Instruct. I will repost to that thread.

Hi folks,
Not sure if this is the best place to ask this question. Please let me know if there is somewhere else. I'll also probably try your support/contact link.

When I use the playground with this model, it works fine.

I then copy the curl command that the playground generates and run that locally and it returns an empty text string for the answer. Here is a sample response. I've tried adjusting the temperature, top_p, top_k, max_tokens, stream_tokens and the prompt that I'm asking.

{"id":"83df4b8d3f94c39c-SEA","status":"finished","prompt":["[INST]  What is rain?  [/INST]  "],"model":"togethercomputer/Llama-2-7B-32K-Instruct","model_owner":"","num_returns":1,"args":{"model":"togethercomputer/Llama-2-7B-32K-Instruct","prompt":"[INST]  What is rain?  [/INST]  ","request_type":"language-model-inference","temperature":0.1,"top_p":0.1,"top_k":3,"max_tokens":1000,"stream_tokens":false,"stop":["[INST]","\n\n"],"negative_prompt":"","sessionKey":"906e58d5-91b6-4ec9-990e-315b47ec5184","update_at":"2023-12-31T03:00:29.376Z"},"subjobs":[],"output":{"usage":{"prompt_tokens":15,"completion_tokens":2,"total_tokens":17},"result_type":"language-model-inference","choices":[{"text":""}]}}%

This also happens when using the javascript code that is generated.

The generated curl command is working correctly for all other models that I have tried.

Thanks for any guidance,
Jeremy

orangetin

Together org Jan 5, 2024

closing -- fixed in the correct model issue.

orangetin changed discussion status to closed Jan 5, 2024

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