Instructions to use TemporalGames/opt-1.3b-lambada_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TemporalGames/opt-1.3b-lambada_base with Transformers:

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

pipe = pipeline("text-generation", model="TemporalGames/opt-1.3b-lambada_base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TemporalGames/opt-1.3b-lambada_base")
model = AutoModelForCausalLM.from_pretrained("TemporalGames/opt-1.3b-lambada_base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TemporalGames/opt-1.3b-lambada_base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TemporalGames/opt-1.3b-lambada_base

SGLang

How to use TemporalGames/opt-1.3b-lambada_base 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 "TemporalGames/opt-1.3b-lambada_base" \
    --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": "TemporalGames/opt-1.3b-lambada_base",
		"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 "TemporalGames/opt-1.3b-lambada_base" \
        --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": "TemporalGames/opt-1.3b-lambada_base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TemporalGames/opt-1.3b-lambada_base with Docker Model Runner:
```
docker model run hf.co/TemporalGames/opt-1.3b-lambada_base
```

PNAKTEMPORAL commited on Aug 29, 2023

Commit

0497db7

1 Parent(s): 54477a1

Create README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md ADDED Viewed

	@@ -0,0 +1,11 @@

+---
+datasets:
+- lambada
+language:
+- en
+---
+{'eval_loss': 7.871013164520264,
+ 'eval_runtime': 5025.0273,
+ 'eval_samples_per_second': 1.025,
+ 'eval_steps_per_second': 0.513,
+ 'epoch': 1.0}