Instructions to use fiel1986/Andromeda-8B-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fiel1986/Andromeda-8B-Coder with Transformers:

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

pipe = pipeline("text-generation", model="fiel1986/Andromeda-8B-Coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fiel1986/Andromeda-8B-Coder")
model = AutoModelForCausalLM.from_pretrained("fiel1986/Andromeda-8B-Coder", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

HERMES

How to use fiel1986/Andromeda-8B-Coder with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fiel1986/Andromeda-8B-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fiel1986/Andromeda-8B-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fiel1986/Andromeda-8B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fiel1986/Andromeda-8B-Coder

SGLang

How to use fiel1986/Andromeda-8B-Coder 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 "fiel1986/Andromeda-8B-Coder" \
    --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": "fiel1986/Andromeda-8B-Coder",
		"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 "fiel1986/Andromeda-8B-Coder" \
        --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": "fiel1986/Andromeda-8B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fiel1986/Andromeda-8B-Coder with Docker Model Runner:
```
docker model run hf.co/fiel1986/Andromeda-8B-Coder
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Andromeda 8B

Andrómeda es una asistente personal optimizada para monitores verticales y dispositivos de bajo consumo, pero en su versión más capaz de 8B.

Merge de 3 de los mejores modelos Instruct de la familia Llama 3.1, enfocada en conversación natural, rol, creatividad y razonamiento en español.

Base del Merge

Este modelo es un merge de:

Meta-Llama-3.1-8B-Instruct - Base sólida de Meta
Llama-3.1-Nemotron-70B-Instruct - Capacidad de razonamiento y ChatQA de NVIDIA
Hermes-3-Llama-3.1-8B - Sigue instrucciones, rol y creatividad sin censura excesiva de Nous

Método: DARE TIES / Model Stock

Características

Excelente en español mexicano / neutro
Buena para roleplay, asistente personal y escritora
Contexto largo de Llama 3.1 (128k)
Más coherente y menos repetitiva que la versión 3B

Cómo usar

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "fiel1986/andromeda-8b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

prompt = " Usuario: Hola, ¿que es la fotosintesis?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))Detalles
Desarrollado por: fiel1986  Licencia: llama3.1 Si te gusta el proyecto, dale ❤️ y Follow!