Instructions to use royleibov/granite-3b-code-base-128k-ZipNN-Compressed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use royleibov/granite-3b-code-base-128k-ZipNN-Compressed with Transformers:

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

pipe = pipeline("text-generation", model="royleibov/granite-3b-code-base-128k-ZipNN-Compressed")

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

tokenizer = AutoTokenizer.from_pretrained("royleibov/granite-3b-code-base-128k-ZipNN-Compressed")
model = AutoModelForCausalLM.from_pretrained("royleibov/granite-3b-code-base-128k-ZipNN-Compressed", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use royleibov/granite-3b-code-base-128k-ZipNN-Compressed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "royleibov/granite-3b-code-base-128k-ZipNN-Compressed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "royleibov/granite-3b-code-base-128k-ZipNN-Compressed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/royleibov/granite-3b-code-base-128k-ZipNN-Compressed

SGLang

How to use royleibov/granite-3b-code-base-128k-ZipNN-Compressed 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 "royleibov/granite-3b-code-base-128k-ZipNN-Compressed" \
    --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": "royleibov/granite-3b-code-base-128k-ZipNN-Compressed",
		"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 "royleibov/granite-3b-code-base-128k-ZipNN-Compressed" \
        --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": "royleibov/granite-3b-code-base-128k-ZipNN-Compressed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use royleibov/granite-3b-code-base-128k-ZipNN-Compressed with Docker Model Runner:
```
docker model run hf.co/royleibov/granite-3b-code-base-128k-ZipNN-Compressed
```

rpand002 commited on Jul 16, 2024

Commit

d929d31

verified ·

1 Parent(s): 601d23d

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -240,7 +240,7 @@ for i in output:
 ```
 ## Training Data
-Starting from the base Granite model, this model was further pretrained on repository-level code data with per-language oversampling, allowing it to effectively utilize up to 128K tokens of context. This continued training stage focused on a curated selection of programming languages, such as Python, C, C++, Go, Java, JavaScript, and TypeScript.
 ## Infrastructure
 We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.

 ```
 ## Training Data
+Starting from the base Granite model, this model was further pretrained on repository-level code data with per-language context-length oversampling, allowing it to effectively utilize up to 128K tokens of context. This continued training stage focused on a curated selection of programming languages, such as Python, C, C++, Go, Java, JavaScript, and TypeScript.
 ## Infrastructure
 We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.