Instructions to use nlpcloud/instruct-gpt-j-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nlpcloud/instruct-gpt-j-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="nlpcloud/instruct-gpt-j-fp16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nlpcloud/instruct-gpt-j-fp16")
model = AutoModelForCausalLM.from_pretrained("nlpcloud/instruct-gpt-j-fp16")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nlpcloud/instruct-gpt-j-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nlpcloud/instruct-gpt-j-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nlpcloud/instruct-gpt-j-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nlpcloud/instruct-gpt-j-fp16

SGLang

How to use nlpcloud/instruct-gpt-j-fp16 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 "nlpcloud/instruct-gpt-j-fp16" \
    --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": "nlpcloud/instruct-gpt-j-fp16",
		"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 "nlpcloud/instruct-gpt-j-fp16" \
        --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": "nlpcloud/instruct-gpt-j-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nlpcloud/instruct-gpt-j-fp16 with Docker Model Runner:
```
docker model run hf.co/nlpcloud/instruct-gpt-j-fp16
```

Empty responses / Zero new tokens generated as output

by sanchimittal - opened Sep 22, 2023

Discussion

sanchimittal

Sep 22, 2023

•

edited Sep 22, 2023

Hello, I am using the Instruct-GPT-J model with <|endoftext|> as eos_token as well as bos_token.
With many input texts I'm getting only <|endoftext|> as output or you could say empty response, as model generates only the input + eos_token. My generate function looks like this:

gen_tokens = model.generate(
        input_ids,
        do_sample=True,
        bos_token_id = 50256,
        eos_token_id = 50256,
        temperature=0.7,
        min_new_tokens = 5,
        max_new_tokens = 2048,
    )
gen_text = tokenizer.batch_decode(gen_tokens)[0]

<|endoftext|> has token id 50256 for the tokenizer.
Tokenizer and model initialization:

tokenizer = AutoTokenizer.from_pretrained("../weights/instruct-gpt-j-fp16/", bos_token='<|endoftext|>', eos_token='<|endoftext|>', pad_token='<|pad|>')
model = AutoModelForCausalLM.from_pretrained("../weights/instruct-gpt-j-fp16/").cuda()
model.resize_token_embeddings(len(tokenizer))

Sometimes it generates good enough output text as well, but like 2/10 times. Can someone please help with why is this issue happening and what can I try to resolve?

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