Bmcbob76/echo-software-adapter

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-7B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "Bmcbob76/echo-software-adapter")

# Generate
messages = [
    {"role": "system", "content": "You are a domain expert in Software Engineering & DevOps."},
    {"role": "user", "content": "Review this microservices architecture for single points of failure, scaling bottlenecks, and recommend improvements for high availability."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.3)

print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

python -m vllm.entrypoints.openai.api_server \
    --model Qwen/Qwen2.5-7B-Instruct \
    --enable-lora \
    --lora-modules 'echo-software-adapter=Bmcbob76/echo-software-adapter'

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
response = client.chat.completions.create(
    model="echo-software-adapter",
    messages=[
        {"role": "system", "content": "You are a domain expert in Software Engineering & DevOps."},
        {"role": "user", "content": "Review this microservices architecture for single points of failure, scaling bottlenecks, and recommend improvements for high availability."},
    ],
    temperature=0.3,
    max_tokens=1024,
)
print(response.choices[0].message.content)