Instructions to use maxcurrent/NeuralMonarchCoderPearlBeagle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maxcurrent/NeuralMonarchCoderPearlBeagle with Transformers:

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

pipe = pipeline("text-generation", model="maxcurrent/NeuralMonarchCoderPearlBeagle")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maxcurrent/NeuralMonarchCoderPearlBeagle")
model = AutoModelForCausalLM.from_pretrained("maxcurrent/NeuralMonarchCoderPearlBeagle")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maxcurrent/NeuralMonarchCoderPearlBeagle with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maxcurrent/NeuralMonarchCoderPearlBeagle"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maxcurrent/NeuralMonarchCoderPearlBeagle",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maxcurrent/NeuralMonarchCoderPearlBeagle

SGLang

How to use maxcurrent/NeuralMonarchCoderPearlBeagle 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 "maxcurrent/NeuralMonarchCoderPearlBeagle" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maxcurrent/NeuralMonarchCoderPearlBeagle",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "maxcurrent/NeuralMonarchCoderPearlBeagle" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maxcurrent/NeuralMonarchCoderPearlBeagle",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maxcurrent/NeuralMonarchCoderPearlBeagle with Docker Model Runner:
```
docker model run hf.co/maxcurrent/NeuralMonarchCoderPearlBeagle
```

Max Current commited on Mar 2, 2024

Commit

758a75c

verified ·

1 Parent(s): 2e74109

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -11,8 +11,11 @@ base_model:
 - eldogbbhed/NeuralPearlBeagle
 ---
-# NeuralMonarchCoderPearlBeagle
 <center><img src='https://i.postimg.cc/K8N1SLYx/ee68f836-5714-4d6f-9646-22f0f7f1601e.png' width='1360px' height='768'></center>
 NeuralMonarchCoderPearlBeagle is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [abideen/MonarchCoder-7B](https://huggingface.co/abideen/MonarchCoder-7B)
 * [eldogbbhed/NeuralPearlBeagle](https://huggingface.co/eldogbbhed/NeuralPearlBeagle)

 - eldogbbhed/NeuralPearlBeagle
 ---
 <center><img src='https://i.postimg.cc/K8N1SLYx/ee68f836-5714-4d6f-9646-22f0f7f1601e.png' width='1360px' height='768'></center>
+# NeuralMonarchCoderPearlBeagle
 NeuralMonarchCoderPearlBeagle is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [abideen/MonarchCoder-7B](https://huggingface.co/abideen/MonarchCoder-7B)
 * [eldogbbhed/NeuralPearlBeagle](https://huggingface.co/eldogbbhed/NeuralPearlBeagle)