Instructions to use raulgdp/qwen2.5-7b-acredita-cna-col with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raulgdp/qwen2.5-7b-acredita-cna-col with Transformers:

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

pipe = pipeline("text-generation", model="raulgdp/qwen2.5-7b-acredita-cna-col")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("raulgdp/qwen2.5-7b-acredita-cna-col")
model = AutoModelForCausalLM.from_pretrained("raulgdp/qwen2.5-7b-acredita-cna-col", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use raulgdp/qwen2.5-7b-acredita-cna-col with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raulgdp/qwen2.5-7b-acredita-cna-col"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raulgdp/qwen2.5-7b-acredita-cna-col",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/raulgdp/qwen2.5-7b-acredita-cna-col

SGLang

How to use raulgdp/qwen2.5-7b-acredita-cna-col 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 "raulgdp/qwen2.5-7b-acredita-cna-col" \
    --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": "raulgdp/qwen2.5-7b-acredita-cna-col",
		"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 "raulgdp/qwen2.5-7b-acredita-cna-col" \
        --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": "raulgdp/qwen2.5-7b-acredita-cna-col",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use raulgdp/qwen2.5-7b-acredita-cna-col with Docker Model Runner:
```
docker model run hf.co/raulgdp/qwen2.5-7b-acredita-cna-col
```

qwen2.5-7b-acredita-cna-col

Fine-tuning de Qwen/Qwen2.5-7B-Instruct sobre 93,829 pares de preguntas y respuestas de acreditación universitaria colombiana.

Especializado en el sistema del Consejo Nacional de Acreditación (CNA), la Escuela de Ingeniería de Sistemas y Computación (EISC) y la Universidad del Valle.

Uso rápido

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "raulgdp/qwen2.5-7b-acredita-cna-col"
tok   = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

messages = [{"role": "user", "content": "¿Cuáles son los factores del CNA?"}]
prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(prompt, return_tensors="pt").to(model.device)

out = model.generate(**inputs, max_new_tokens=300,
                     do_sample=False, repetition_penalty=1.15)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Con Ollama

ollama run raulgdp/qwen2.5-7b-acredita-cna-col

Entrenamiento

Parametro	Valor
Modelo base	Qwen/Qwen2.5-7B-Instruct
Metodo	SFT + LoRA
Dataset	93,829 pares Q&A acreditacion CNA
LoRA rank	32
Epochs	3
Hardware	RTX 4090 24GB
Generador Q&A	Qwen2.5-7B-Instruct