Instructions to use anujsahani01/codegen_finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anujsahani01/codegen_finetune with Transformers:

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

pipe = pipeline("text-generation", model="anujsahani01/codegen_finetune")

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

tokenizer = AutoTokenizer.from_pretrained("anujsahani01/codegen_finetune")
model = AutoModelForCausalLM.from_pretrained("anujsahani01/codegen_finetune", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anujsahani01/codegen_finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anujsahani01/codegen_finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anujsahani01/codegen_finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/anujsahani01/codegen_finetune

SGLang

How to use anujsahani01/codegen_finetune 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 "anujsahani01/codegen_finetune" \
    --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": "anujsahani01/codegen_finetune",
		"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 "anujsahani01/codegen_finetune" \
        --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": "anujsahani01/codegen_finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use anujsahani01/codegen_finetune with Docker Model Runner:
```
docker model run hf.co/anujsahani01/codegen_finetune
```

codegen_finetune

Commit History

Jun 25, 2023

09:48
Adding `safetensors` variant of this model⁠

SFconvertbot

ced2701

Jun 20, 2023

14:42
Update README.md

anujsahani01

fd93fe8

Jun 19, 2023

00:11
update model card README.md

anujsahani01

93befe7
00:10
End of training

anujsahani01

22844bc

Jun 18, 2023

23:59
Training in progress, step 4500

anujsahani01

2625b89
23:45
Training in progress, step 4000

anujsahani01

43b6be8
23:31
Training in progress, step 3500

anujsahani01

98465d3
23:17
Training in progress, step 3000

anujsahani01

a662286
23:03
Training in progress, step 2500

anujsahani01

843df49
22:49
Training in progress, step 2000

anujsahani01

eeeeac0
22:35
Training in progress, step 1500

anujsahani01

3284d67
22:21
Training in progress, step 1000

anujsahani01

0c1a331
22:07
Training in progress, step 500

anujsahani01

79d8ea5
21:47
Training in progress, step 500

anujsahani01

28903b1
21:11
initial commit

anujsahani01

24b3601

Commit History

Jun 25, 2023

Adding `safetensors` variant of this model⁠

Jun 20, 2023

Update README.md

Jun 19, 2023

update model card README.md

End of training

Jun 18, 2023

Training in progress, step 4500

Training in progress, step 4000

Training in progress, step 3500

Training in progress, step 3000

Training in progress, step 2500

Training in progress, step 2000

Training in progress, step 1500

Training in progress, step 1000

Training in progress, step 500

Training in progress, step 500

initial commit