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

Libraries

How to use michaelfeil/ct2fast-starcoder with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("michaelfeil/ct2fast-starcoder")
model = AutoModelForCausalLM.from_pretrained("michaelfeil/ct2fast-starcoder")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use michaelfeil/ct2fast-starcoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelfeil/ct2fast-starcoder"
# 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-starcoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/michaelfeil/ct2fast-starcoder

SGLang

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

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

michaelfeil commited on May 30, 2023

Commit

0e006ee

1 Parent(s): 5aefbdc

Upload bigcode/starcoder ctranslate fp16 weights

Browse files

Files changed (3) hide show

README.md +4 -4
model.bin +2 -2
vocab.json +0 -0

README.md CHANGED Viewed

@@ -266,12 +266,12 @@ quantized version of [bigcode/starcoder](https://huggingface.co/bigcode/starcode
 ```bash
 pip install hf-hub-ctranslate2>=2.0.8
 ```
-Converted on 2023-05-23 using
 ```
-ct2-transformers-converter --model bigcode/starcoder --output_dir /home/michael/tmp-ct2fast-starcoder --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json generation_config.json special_tokens_map.json .gitattributes --quantization float16
 ```
-Checkpoint compatible to [ctranslate2>=3.14.0](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2>=2.0.6](https://github.com/michaelfeil/hf-hub-ctranslate2)
 - `compute_type=int8_float16` for `device="cuda"`
 - `compute_type=int8`  for `device="cpu"`
@@ -289,7 +289,7 @@ model = GeneratorCT2fromHfHub(
         # tokenizer=AutoTokenizer.from_pretrained("bigcode/starcoder")
 )
 outputs = model.generate(
-    text=["def hello_world()", "User: How are you doing? Bot:"],
     max_length=64
 )
 print(outputs)

 ```bash
 pip install hf-hub-ctranslate2>=2.0.8
 ```
+Converted on 2023-05-30 using
 ```
+ct2-transformers-converter --model bigcode/starcoder --output_dir /home/michael/tmp-ct2fast-starcoder --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json vocab.json generation_config.json special_tokens_map.json .gitattributes --quantization float16 --trust_remote_code
 ```
+Checkpoint compatible to [ctranslate2>=3.14.0](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2>=2.0.8](https://github.com/michaelfeil/hf-hub-ctranslate2)
 - `compute_type=int8_float16` for `device="cuda"`
 - `compute_type=int8`  for `device="cpu"`
         # tokenizer=AutoTokenizer.from_pretrained("bigcode/starcoder")
 )
 outputs = model.generate(
+    text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
     max_length=64
 )
 print(outputs)

model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10b6e28e73c9e407636e8d3988c1f60dc9b1767f8c7aaaca18693144c3dd188
-size 36949870923

 version https://git-lfs.github.com/spec/v1
+oid sha256:4957219992c0e64cdc513ae4e2e5b31814cb49505af551672345708ed4e33621
+size 31034941879

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff