Instructions to use michaelfeil/ct2fast-gpt_bigcode-santacoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaelfeil/ct2fast-gpt_bigcode-santacoder with Transformers:

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

pipe = pipeline("text-generation", model="michaelfeil/ct2fast-gpt_bigcode-santacoder")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("michaelfeil/ct2fast-gpt_bigcode-santacoder", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use michaelfeil/ct2fast-gpt_bigcode-santacoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelfeil/ct2fast-gpt_bigcode-santacoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelfeil/ct2fast-gpt_bigcode-santacoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/michaelfeil/ct2fast-gpt_bigcode-santacoder

SGLang

How to use michaelfeil/ct2fast-gpt_bigcode-santacoder 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 "michaelfeil/ct2fast-gpt_bigcode-santacoder" \
    --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": "michaelfeil/ct2fast-gpt_bigcode-santacoder",
		"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 "michaelfeil/ct2fast-gpt_bigcode-santacoder" \
        --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": "michaelfeil/ct2fast-gpt_bigcode-santacoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use michaelfeil/ct2fast-gpt_bigcode-santacoder with Docker Model Runner:
```
docker model run hf.co/michaelfeil/ct2fast-gpt_bigcode-santacoder
```

michaelfeil commited on May 31, 2023

Commit

368b912

1 Parent(s): 71be13b

Upload bigcode/gpt_bigcode-santacoder ctranslate fp16 weights

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -173,9 +173,9 @@ Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on
 quantized version of [bigcode/gpt_bigcode-santacoder](https://huggingface.co/bigcode/gpt_bigcode-santacoder)
 ```bash
-pip install hf-hub-ctranslate2>=2.0.8
 ```
-Converted on 2023-05-30 using
 ```
 ct2-transformers-converter --model bigcode/gpt_bigcode-santacoder --output_dir /home/michael/tmp-ct2fast-gpt_bigcode-santacoder --force --copy_files tokenizer.json README.md tokenizer_config.json special_tokens_map.json .gitattributes --quantization float16 --trust_remote_code
 ```
@@ -199,7 +199,8 @@ model = GeneratorCT2fromHfHub(
 )
 outputs = model.generate(
     text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
-    max_length=64
 )
 print(outputs)
 ```

 quantized version of [bigcode/gpt_bigcode-santacoder](https://huggingface.co/bigcode/gpt_bigcode-santacoder)
 ```bash
+pip install hf-hub-ctranslate2>=2.0.8 ctranslate2>=3.14.0
 ```
+Converted on 2023-05-31 using
 ```
 ct2-transformers-converter --model bigcode/gpt_bigcode-santacoder --output_dir /home/michael/tmp-ct2fast-gpt_bigcode-santacoder --force --copy_files tokenizer.json README.md tokenizer_config.json special_tokens_map.json .gitattributes --quantization float16 --trust_remote_code
 ```
 )
 outputs = model.generate(
     text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
+    max_length=64,
+    include_prompt_in_result=False
 )
 print(outputs)
 ```