Instructions to use BlackSamorez/codegen-16B-multi-6-parts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BlackSamorez/codegen-16B-multi-6-parts with Transformers:

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

pipe = pipeline("text-generation", model="BlackSamorez/codegen-16B-multi-6-parts")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BlackSamorez/codegen-16B-multi-6-parts")
model = AutoModelForCausalLM.from_pretrained("BlackSamorez/codegen-16B-multi-6-parts")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BlackSamorez/codegen-16B-multi-6-parts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BlackSamorez/codegen-16B-multi-6-parts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BlackSamorez/codegen-16B-multi-6-parts",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BlackSamorez/codegen-16B-multi-6-parts

SGLang

How to use BlackSamorez/codegen-16B-multi-6-parts 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 "BlackSamorez/codegen-16B-multi-6-parts" \
    --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": "BlackSamorez/codegen-16B-multi-6-parts",
		"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 "BlackSamorez/codegen-16B-multi-6-parts" \
        --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": "BlackSamorez/codegen-16B-multi-6-parts",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BlackSamorez/codegen-16B-multi-6-parts with Docker Model Runner:
```
docker model run hf.co/BlackSamorez/codegen-16B-multi-6-parts
```

codegen-16B-multi-6-parts

Commit History

tokenizer and such

d6e09e8

Andrei Panferov commited on Mar 24, 2023

weights

2f56b8d

Andrei Panferov commited on Mar 24, 2023

metadata

6f5cd8e

Andrei Panferov commited on Mar 24, 2023

initial commit

ee7ff1a

Andrei Panferov commited on Mar 24, 2023

Commit History

tokenizer and such d6e09e8

weights 2f56b8d

metadata 6f5cd8e

initial commit ee7ff1a

tokenizer and such

d6e09e8

weights

2f56b8d

metadata

6f5cd8e

initial commit

ee7ff1a