Instructions to use blue-tundra-42/code_and_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blue-tundra-42/code_and_model with Transformers:

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

pipe = pipeline("text-generation", model="blue-tundra-42/code_and_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("blue-tundra-42/code_and_model")
model = AutoModelForCausalLM.from_pretrained("blue-tundra-42/code_and_model")
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 blue-tundra-42/code_and_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blue-tundra-42/code_and_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blue-tundra-42/code_and_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blue-tundra-42/code_and_model

SGLang

How to use blue-tundra-42/code_and_model 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 "blue-tundra-42/code_and_model" \
    --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": "blue-tundra-42/code_and_model",
		"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 "blue-tundra-42/code_and_model" \
        --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": "blue-tundra-42/code_and_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use blue-tundra-42/code_and_model with Docker Model Runner:
```
docker model run hf.co/blue-tundra-42/code_and_model
```

code_and_model

File size: 964 Bytes

f1f682e

# models/__init__.py

from .base_model import BaseModel
from .qwen_2d5_omni_7b import Qwen2_5Omni7B
from .vllm_client import VLLMClient
from .uno_scorer_hf import UNOScorerHF

# Model name to class mapping
MODEL_REGISTRY = {
    "Qwen-2.5-Omni-7B": Qwen2_5Omni7B,
    "VLLMClient": VLLMClient,
    "UNOScorerHF":UNOScorerHF
}

def get_model(model_name: str, model_path: str, **kwargs) -> BaseModel:
    """
    Model factory function.

    :param model_name: Registered model name (e.g., 'qwen_api')
    :param model_path: Actual model path or API identifier (e.g., 'qwen-turbo')
    :param kwargs: Other model initialization parameters
    :return: Instance of BaseModel
    """
    if model_name not in MODEL_REGISTRY:
        raise ValueError(f"Unknown model name: {model_name}. Available models: {list(MODEL_REGISTRY.keys())}")
        
    model_class = MODEL_REGISTRY[model_name]
    return model_class(model_name=model_name, model_path=model_path, **kwargs)