Instructions to use oakela/finetune_starcoder2_nate_continue_600steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oakela/finetune_starcoder2_nate_continue_600steps with Transformers:

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

pipe = pipeline("text-generation", model="oakela/finetune_starcoder2_nate_continue_600steps")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oakela/finetune_starcoder2_nate_continue_600steps")
model = AutoModelForCausalLM.from_pretrained("oakela/finetune_starcoder2_nate_continue_600steps")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use oakela/finetune_starcoder2_nate_continue_600steps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oakela/finetune_starcoder2_nate_continue_600steps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oakela/finetune_starcoder2_nate_continue_600steps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/oakela/finetune_starcoder2_nate_continue_600steps

SGLang

How to use oakela/finetune_starcoder2_nate_continue_600steps 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 "oakela/finetune_starcoder2_nate_continue_600steps" \
    --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": "oakela/finetune_starcoder2_nate_continue_600steps",
		"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 "oakela/finetune_starcoder2_nate_continue_600steps" \
        --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": "oakela/finetune_starcoder2_nate_continue_600steps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use oakela/finetune_starcoder2_nate_continue_600steps with Docker Model Runner:
```
docker model run hf.co/oakela/finetune_starcoder2_nate_continue_600steps
```

oakela commited on Mar 17, 2024

Commit

f17bb71

verified ·

1 Parent(s): 3addc05

Delete final_checkpoint/generation_config.json

Browse files

Files changed (1) hide show

final_checkpoint/generation_config.json +0 -6

final_checkpoint/generation_config.json DELETED Viewed

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
-  "transformers_version": "4.39.0.dev0"
-}