Instructions to use swype/deepshard-65B-raw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use swype/deepshard-65B-raw with Transformers:

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

pipe = pipeline("text-generation", model="swype/deepshard-65B-raw")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("swype/deepshard-65B-raw")
model = AutoModelForCausalLM.from_pretrained("swype/deepshard-65B-raw")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use swype/deepshard-65B-raw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "swype/deepshard-65B-raw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "swype/deepshard-65B-raw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/swype/deepshard-65B-raw

SGLang

How to use swype/deepshard-65B-raw 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 "swype/deepshard-65B-raw" \
    --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": "swype/deepshard-65B-raw",
		"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 "swype/deepshard-65B-raw" \
        --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": "swype/deepshard-65B-raw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use swype/deepshard-65B-raw with Docker Model Runner:
```
docker model run hf.co/swype/deepshard-65B-raw
```

deepshard-65B-raw

Commit History

fix

d4aa6f6

Ubuntu commited on Mar 9, 2023

added tokenizer

0d5ef7c

Ubuntu commited on Mar 8, 2023

Hello world

aece7f1

Ubuntu commited on Mar 8, 2023

initial commit

8164323

Srikanth Srinivas commited on Mar 8, 2023

Commit History

fix d4aa6f6

added tokenizer 0d5ef7c

Hello world aece7f1

initial commit 8164323

fix

d4aa6f6

added tokenizer

0d5ef7c

Hello world

aece7f1

initial commit

8164323