Instructions to use Danielbrdz/Barcenas-14b-phi-4-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Danielbrdz/Barcenas-14b-phi-4-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Danielbrdz/Barcenas-14b-phi-4-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Danielbrdz/Barcenas-14b-phi-4-v2")
model = AutoModelForCausalLM.from_pretrained("Danielbrdz/Barcenas-14b-phi-4-v2")
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 Danielbrdz/Barcenas-14b-phi-4-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Danielbrdz/Barcenas-14b-phi-4-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Danielbrdz/Barcenas-14b-phi-4-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Danielbrdz/Barcenas-14b-phi-4-v2

SGLang

How to use Danielbrdz/Barcenas-14b-phi-4-v2 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 "Danielbrdz/Barcenas-14b-phi-4-v2" \
    --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": "Danielbrdz/Barcenas-14b-phi-4-v2",
		"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 "Danielbrdz/Barcenas-14b-phi-4-v2" \
        --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": "Danielbrdz/Barcenas-14b-phi-4-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Danielbrdz/Barcenas-14b-phi-4-v2 with Docker Model Runner:
```
docker model run hf.co/Danielbrdz/Barcenas-14b-phi-4-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Barcenas 14b phi-4 v2

Based on pankajmathur/orca_mini_phi-4 And trained with the dataset mlabonne/OpenThoughts-79k-filtered

The goal of this new model is to work around the bugs of the first version, using a better base and a much larger dataset containing related quality data covering math, science, code and puzzles.

This new version is expected to perform much better than the first version and achieve better benchmark results.

Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽

Downloads last month: 3

Safetensors

Model size

15B params

Tensor type

F16

Model tree for Danielbrdz/Barcenas-14b-phi-4-v2

Base model

microsoft/phi-4

Finetuned

(96)

this model

Quantizations

2 models

Danielbrdz
/

Barcenas-14b-phi-4-v2

Model tree for Danielbrdz/Barcenas-14b-phi-4-v2

Dataset used to train Danielbrdz/Barcenas-14b-phi-4-v2