Instructions to use Ponyyyy/language-modeling-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ponyyyy/language-modeling-model with Transformers:

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

pipe = pipeline("text-generation", model="Ponyyyy/language-modeling-model")

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

tokenizer = AutoTokenizer.from_pretrained("Ponyyyy/language-modeling-model")
model = AutoModelForCausalLM.from_pretrained("Ponyyyy/language-modeling-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ponyyyy/language-modeling-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ponyyyy/language-modeling-model

SGLang

How to use Ponyyyy/language-modeling-model 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 "Ponyyyy/language-modeling-model" \
    --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": "Ponyyyy/language-modeling-model",
		"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 "Ponyyyy/language-modeling-model" \
        --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": "Ponyyyy/language-modeling-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ponyyyy/language-modeling-model with Docker Model Runner:
```
docker model run hf.co/Ponyyyy/language-modeling-model
```

Ponyyyy commited on Apr 26, 2024

Commit

7e73ea5

verified ·

1 Parent(s): 253ad0e

Training in progress, step 1500

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Apr26_04-28-00_4643bc53c803/events.out.tfevents.1714105680.4643bc53c803.241.5 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af170ce5c060991055819a8da87efe26512d96303f9f6e1bd5f654cb62d54013
 size 57534056

 version https://git-lfs.github.com/spec/v1
+oid sha256:2b23fbb9d4e206045fe913fbbe40862d2099b04993c8e7ae659aa6acfe6f8f3b
 size 57534056

runs/Apr26_04-28-00_4643bc53c803/events.out.tfevents.1714105680.4643bc53c803.241.5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51de05c3a8cf70b02d7f8cd6e3b9f7af3f9d893fd6046297822150f9dee2ce4c
-size 5461

 version https://git-lfs.github.com/spec/v1
+oid sha256:9089c342fec009ec0d60feb5b9808ed72d0b359a7bbbe18842619e967b459329
+size 5943