Instructions to use umm-maybe/ey_lw_posts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umm-maybe/ey_lw_posts with Transformers:

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

pipe = pipeline("text-generation", model="umm-maybe/ey_lw_posts")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("umm-maybe/ey_lw_posts")
model = AutoModelForCausalLM.from_pretrained("umm-maybe/ey_lw_posts", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use umm-maybe/ey_lw_posts with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/umm-maybe/ey_lw_posts

SGLang

How to use umm-maybe/ey_lw_posts 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 "umm-maybe/ey_lw_posts" \
    --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": "umm-maybe/ey_lw_posts",
		"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 "umm-maybe/ey_lw_posts" \
        --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": "umm-maybe/ey_lw_posts",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umm-maybe/ey_lw_posts with Docker Model Runner:
```
docker model run hf.co/umm-maybe/ey_lw_posts
```

ey_lw_posts

Commit History

Jun 25, 2023

03:21
Adding `safetensors` variant of this model⁠

SFconvertbot

73a38a6

Dec 1, 2022

02:23
Update model

umm-maybe

445415e

Nov 30, 2022

17:56
Delete vocab.json:Zone.Identifier

umm-maybe

5f54bdb
17:56
Delete training_args.bin:Zone.Identifier

umm-maybe

71e2e70
17:56
Delete tokenizer_config.json:Zone.Identifier

umm-maybe

770dce5
17:56
Delete special_tokens_map.json:Zone.Identifier

umm-maybe

037fe83
17:56
Delete pytorch_model.bin:Zone.Identifier

umm-maybe

47685ee
17:56
Delete model_args.json:Zone.Identifier

umm-maybe

6ede3c1
17:55
Delete merges.txt:Zone.Identifier

umm-maybe

4d40e8f
17:55
Delete eval_results.txt:Zone.Identifier

umm-maybe

00e1a29
17:55
Delete config.json:Zone.Identifier

umm-maybe

0471502
05:32
Add model files

umm-maybe

e0f0d39
05:20
initial commit

umm-maybe

22dfa21

Commit History

Jun 25, 2023

Adding `safetensors` variant of this model⁠

Dec 1, 2022

Update model

Nov 30, 2022

Delete vocab.json:Zone.Identifier

Delete training_args.bin:Zone.Identifier

Delete tokenizer_config.json:Zone.Identifier

Delete special_tokens_map.json:Zone.Identifier

Delete pytorch_model.bin:Zone.Identifier

Delete model_args.json:Zone.Identifier

Delete merges.txt:Zone.Identifier

Delete eval_results.txt:Zone.Identifier

Delete config.json:Zone.Identifier

Add model files

initial commit