Instructions to use bmwlab-ntust/log_copilot_32b_with_rag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bmwlab-ntust/log_copilot_32b_with_rag with Transformers:

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

pipe = pipeline("text-generation", model="bmwlab-ntust/log_copilot_32b_with_rag")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bmwlab-ntust/log_copilot_32b_with_rag")
model = AutoModelForCausalLM.from_pretrained("bmwlab-ntust/log_copilot_32b_with_rag")
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 bmwlab-ntust/log_copilot_32b_with_rag with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bmwlab-ntust/log_copilot_32b_with_rag"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bmwlab-ntust/log_copilot_32b_with_rag",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bmwlab-ntust/log_copilot_32b_with_rag

SGLang

How to use bmwlab-ntust/log_copilot_32b_with_rag 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 "bmwlab-ntust/log_copilot_32b_with_rag" \
    --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": "bmwlab-ntust/log_copilot_32b_with_rag",
		"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 "bmwlab-ntust/log_copilot_32b_with_rag" \
        --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": "bmwlab-ntust/log_copilot_32b_with_rag",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bmwlab-ntust/log_copilot_32b_with_rag with Docker Model Runner:
```
docker model run hf.co/bmwlab-ntust/log_copilot_32b_with_rag
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

log_copilot_32b_with_rag

A log-analysis copilot built on Qwen/QwQ-32B via SFT on RAG-style data, intended for log triage, troubleshooting, and root-cause analysis.

Create a virtual environment and install the model

python3.12 -m venv .venv

source .venv/bin/activate

pip install --upgrade pip

pip install -r requirements.txt

Login huggingface

  hf auth login

Install model

hf download bmwlab-ntust/log_copilot_32b_with_rag --local-dir /home/dgx/johnson/models/log_copilot_32b

Start API Server

python3 -m vllm.entrypoints.openai.api_server \
    --model /home/dgx/johnson/models/log_copilot_32b \
    --max-model-len 4096 \
    --dtype bfloat16 \
    --port 8000
    --gpu-memory-utilization 0.8

Testing API

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "/home/dgx/johnson/models/log_copilot_32b",
        "messages": [
            {"role": "user", "content": "Here is a snippet of OAI gNB error log: [ERROR] RRC Connection Reestablishment Reject. Which parameter configuration might be misconfigured, and how can I fix the gNB configuration?"}
        ],
        "temperature": 0.2,
        "max_tokens": 1024
    }'

Monitoring GPU

watch -n 2 nvidia-smi

Downloads last month: 6

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for bmwlab-ntust/log_copilot_32b_with_rag

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/QwQ-32B

Finetuned

(97)

this model