Instructions to use instruction-pretrain/InstructLM-1.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use instruction-pretrain/InstructLM-1.3B with Transformers:

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

pipe = pipeline("text-generation", model="instruction-pretrain/InstructLM-1.3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("instruction-pretrain/InstructLM-1.3B")
model = AutoModelForCausalLM.from_pretrained("instruction-pretrain/InstructLM-1.3B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use instruction-pretrain/InstructLM-1.3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "instruction-pretrain/InstructLM-1.3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "instruction-pretrain/InstructLM-1.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/instruction-pretrain/InstructLM-1.3B

SGLang

How to use instruction-pretrain/InstructLM-1.3B 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 "instruction-pretrain/InstructLM-1.3B" \
    --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": "instruction-pretrain/InstructLM-1.3B",
		"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 "instruction-pretrain/InstructLM-1.3B" \
        --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": "instruction-pretrain/InstructLM-1.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use instruction-pretrain/InstructLM-1.3B with Docker Model Runner:
```
docker model run hf.co/instruction-pretrain/InstructLM-1.3B
```

cannot use or download model model-00001-of-00002.safetensors

by Sakura77 - opened Jun 22, 2024

Discussion

Sakura77

Jun 22, 2024

Error: Api error with status 403. URL: https://cdn-lfs-us-1.huggingface.co/repos/aa/03/aa036474482e60d7978a206bc4089c0493fee7e97a13b95b593ef09aaa2f5489/127f1b69e741ce178bbf059d9b40db9bbf6752d4eef4bf7653a252a320f0cbb7?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00001-of-00002.safetensors%3B+filename%3D%22model-00001-of-00002.safetensors%22%3B&Expires=1719302679&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxOTMwMjY3OX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2FhLzAzL2FhMDM2NDc0NDgyZTYwZDc5NzhhMjA2YmM0MDg5YzA0OTNmZWU3ZTk3YTEzYjk1YjU5M2VmMDlhYWEyZjU0ODkvMTI3ZjFiNjllNzQxY2UxNzhiYmYwNTlkOWI0MGRiOWJiZjY3NTJkNGVlZjRiZjc2NTNhMjUyYTMyMGYwY2JiNz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=srt81BxCTdEe-LlUKcqA8dAXI

instruction-pretrain

Owner Jun 22, 2024

Thanks so much for reporting this, I've updated the model weights.

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