Instructions to use NOVA-vision-language/PlanLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NOVA-vision-language/PlanLLM with Transformers:

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

pipe = pipeline("text-generation", model="NOVA-vision-language/PlanLLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NOVA-vision-language/PlanLLM")
model = AutoModelForCausalLM.from_pretrained("NOVA-vision-language/PlanLLM")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NOVA-vision-language/PlanLLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NOVA-vision-language/PlanLLM

SGLang

How to use NOVA-vision-language/PlanLLM 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 "NOVA-vision-language/PlanLLM" \
    --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": "NOVA-vision-language/PlanLLM",
		"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 "NOVA-vision-language/PlanLLM" \
        --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": "NOVA-vision-language/PlanLLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NOVA-vision-language/PlanLLM with Docker Model Runner:
```
docker model run hf.co/NOVA-vision-language/PlanLLM
```

dmgcsilva commited on Feb 2, 2024

Commit

ac0f1db

verified ·

1 Parent(s): 79041a8

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -3

README.md CHANGED Viewed

@@ -4,7 +4,23 @@ language:
 - en
 ---
-This is under construction.
-This is PlanLLM, a model trained to, given a recipe or a DIY task, help the user complete it in a conversational setting, answering questions and clarifying any doubts.
-This was trained based on a Vicuna with SFT and DPO training.

 - en
 ---
+# PlanLLM
+### Model Details
+PlanLLM is a conversational assistant trained to assist users in completing a recipe from beginning to end and be able to answer any related or relevant requests that the user might have.
+The model was also tested with DIY Tasks and performed similarly.
+#### Training
+PlanLLM was trained by fine-tuning a [Vicuna](https://huggingface.co/lmsys/vicuna-7b-v1.1) model on synthetic dialogue between users and an assistant about a given recipe.
+The model was first trained using SFT and then using Direct Preference Optimization (DPO).
+#### License
+It's the same as Vicuna. A non-commercial Apache 2.0 license.
+#### Paper
+"Plan-Grounded Large Language Models for Dual Goal Conversational Settings" (Accepted at EACL 2024)
+Diogo Glória-Silva, Rafael Ferreira, Diogo Tavares, David Semedo, João Magalhães