Instructions to use ArmelR/starcoder-gradio-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArmelR/starcoder-gradio-v0 with Transformers:

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

pipe = pipeline("text-generation", model="ArmelR/starcoder-gradio-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArmelR/starcoder-gradio-v0")
model = AutoModelForCausalLM.from_pretrained("ArmelR/starcoder-gradio-v0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArmelR/starcoder-gradio-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArmelR/starcoder-gradio-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArmelR/starcoder-gradio-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArmelR/starcoder-gradio-v0

SGLang

How to use ArmelR/starcoder-gradio-v0 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 "ArmelR/starcoder-gradio-v0" \
    --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": "ArmelR/starcoder-gradio-v0",
		"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 "ArmelR/starcoder-gradio-v0" \
        --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": "ArmelR/starcoder-gradio-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArmelR/starcoder-gradio-v0 with Docker Model Runner:
```
docker model run hf.co/ArmelR/starcoder-gradio-v0
```

ArmelR commited on Aug 8, 2023

Commit

ee5b3a4

1 Parent(s): cd72499

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -76,6 +76,18 @@ outputs = model.generate(
 input_len=len(inputs["input_ids"])
 print(tokenizer.decode(outputs[0][input_len:]))
 ```
 # More information
 For further information, refer to [StarCoder](https://huggingface.co/bigcode/starcoder).

 input_len=len(inputs["input_ids"])
 print(tokenizer.decode(outputs[0][input_len:]))
 ```
+# Updates
+Gradio dataset `.filter(lambda x : ("gradio" in x["content"] or "gr." in x["content"]) and "streamlit" not in x["content"]`)
+Guanaco `ArmelR/oasst1_guanaco`
+- StarCoderbase (950, 1350)
+  - max_steps = 2000
+  - shuffle_buffer = 100
+  - batch_size = 2
+  - gradient_accumulation_steps = 4
+  - num_warmup_steps = 100
+  - weight_decay = 0.01
+- StarCoderplus (2000)
+Guanaco multi-turn (HuggingFaceH4/oasst1_en)
 # More information
 For further information, refer to [StarCoder](https://huggingface.co/bigcode/starcoder).