Instructions to use nolanoAI/lordcoder-v0-13-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nolanoAI/lordcoder-v0-13-8B with Transformers:

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

pipe = pipeline("text-generation", model="nolanoAI/lordcoder-v0-13-8B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nolanoAI/lordcoder-v0-13-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nolanoAI/lordcoder-v0-13-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nolanoAI/lordcoder-v0-13-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nolanoAI/lordcoder-v0-13-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nolanoAI/lordcoder-v0-13-8B

SGLang

How to use nolanoAI/lordcoder-v0-13-8B 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 "nolanoAI/lordcoder-v0-13-8B" \
    --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": "nolanoAI/lordcoder-v0-13-8B",
		"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 "nolanoAI/lordcoder-v0-13-8B" \
        --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": "nolanoAI/lordcoder-v0-13-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nolanoAI/lordcoder-v0-13-8B with Docker Model Runner:
```
docker model run hf.co/nolanoAI/lordcoder-v0-13-8B
```

LoRDCoder v0 13.8B

Usage:

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"

model = AutoModelForCausalLM.from_pretrained("nolanoAI/lordcoder-v0-13-8B", trust_remote_code=True).to(device)
tokenizer = AutoTokenizer.from_pretrained("nolanoAI/lordcoder-v0-13-8B", trust_remote_code=True)

inputs = {k: v.to(device) for k,v in tokenizer('# PyTorch CNN on MNIST\nimport torch\n', return_tensors='pt').items()}

generated_ids = model.generate(
        **inputs,
        use_cache=True,
        max_new_tokens=500,
        temperature=0.1,
        top_p=0.95,
        do_sample=True,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.eos_token_id,
    )

Downloads last month: 10

Collection including nolanoAI/lordcoder-v0-13-8B

LoRD

Collection

6 items • Updated Sep 29, 2024