Instructions to use Tonit23/antonio-phi2-bitagent-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tonit23/antonio-phi2-bitagent-merged with Transformers:

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

pipe = pipeline("text-generation", model="Tonit23/antonio-phi2-bitagent-merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tonit23/antonio-phi2-bitagent-merged")
model = AutoModelForCausalLM.from_pretrained("Tonit23/antonio-phi2-bitagent-merged", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tonit23/antonio-phi2-bitagent-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tonit23/antonio-phi2-bitagent-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tonit23/antonio-phi2-bitagent-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tonit23/antonio-phi2-bitagent-merged

SGLang

How to use Tonit23/antonio-phi2-bitagent-merged 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 "Tonit23/antonio-phi2-bitagent-merged" \
    --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": "Tonit23/antonio-phi2-bitagent-merged",
		"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 "Tonit23/antonio-phi2-bitagent-merged" \
        --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": "Tonit23/antonio-phi2-bitagent-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tonit23/antonio-phi2-bitagent-merged with Docker Model Runner:
```
docker model run hf.co/Tonit23/antonio-phi2-bitagent-merged
```

antonio-phi2-bitagent-merged / README.md

Tonit23

Actualizo descripción completa del modelo SN20

aa6a322 9 months ago

preview code

Raw

History Blame Contribute Delete

2.43 kB

	---
	pipeline_tag: text-generation
	license: mit
	language:
	- es
	- en
	tags:
	- bittensor
	- subnet-20
	- bitagent
	- phi2
	- lora
	- bfcl
	- tool-calling
	base_model: microsoft/phi-2
	library_name: transformers
	model_type: causal-lm
	inference: true
	---

	# 🚀 Antonio Phi-2 BitAgent Merged (Subnet-20)

	Autor: [@Tonit23](https://huggingface.co/Tonit23)
	Base: `microsoft/phi-2`
	Fine-tune: [`antonio-phi2-bitagent-lora`](https://huggingface.co/Tonit23/antonio-phi2-bitagent-lora)
	Subnet: 🧠 [Bittensor Subnet-20 — BitAgent](https://rizzo.network/subnet-20/)
	Publicación: octubre 2025

	---

	## 🧩 Descripción general

	`antonio-phi2-bitagent-merged` es una versión LoRA-fusionada del modelo `microsoft/phi-2`, adaptada específicamente para el entorno BitAgent (SN20) dentro del ecosistema Bittensor Finney.

	Este modelo está optimizado para tareas de razonamiento en español e inglés, inferencia compacta y tool-calling semántico (uso de funciones o herramientas internas), usando un esquema compatible con los validadores SN20.

	---

	## ⚙️ Detalles técnicos

	\| Propiedad \| Valor \|
	\|-------------------------\|-------\|
	\| Modelo base \| `microsoft/phi-2` \|
	\| Fine-tune \| `LoRA` sobre dataset de prompts técnicos BFCL \|
	\| Parámetros totales \| ~7.24 B \|
	\| Parámetros entrenables \| 3.4 M (0.047 %) \|
	\| Framework \| PyTorch + Transformers + PEFT \|
	\| Licencia \| MIT \|
	\| Hardware objetivo \| CPU / GPU (float16) \|

	### Entrenamiento
	El modelo fue fine-tuneado con LoRA (Low-Rank Adaptation) en un conjunto de datos mixto de tareas técnicas:
	- prompts de razonamiento lógico, instrucciones BFCL y tool-calling
	- pares entrada/salida basados en análisis ABAP y Python
	- mezclas en español e inglés

	---

	## 🧠 Uso

	### Inferencia local (Transformers)

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	model = AutoModelForCausalLM.from_pretrained("Tonit23/antonio-phi2-bitagent-merged", torch_dtype=torch.float16)
	tokenizer = AutoTokenizer.from_pretrained("Tonit23/antonio-phi2-bitagent-merged")

	prompt = "Explica el proceso de staking en la red Bittensor Finney:"
	inputs = tokenizer(prompt, return_tensors="pt")

	outputs = model.generate(**inputs, max_new_tokens=200)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))