Ba2han/muon-lora-2

Model Card for Model ID

Model Details

Model Description

• Developed by: Ba2han
• Funded by [optional]: None
• Model type: SLM
• Language(s) (NLP): English, Turkish
• License: MIT
• Finetuned from model [optional]: Ba2han/test-model-muon

How to Get Started with the Model

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

BASE_MODEL_PATH = "Ba2han/test-model-muon"
LORA_PATH = "Ba2han/muon-lora-2"

model = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL_PATH,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    load_in_4bit=False,
    low_cpu_mem_usage=True,
)


tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL_PATH)
model = PeftModel.from_pretrained(model, LORA_PATH)

chat_pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "Sen bir asistansın. Kısa ve doğru cevaplar ver."},
    {"role": "user", "content": "5+1 kaç eder?"},
]

# Convert to plain text for pipeline
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# --- Generate ---
outputs = chat_pipe(
    prompt,
    max_new_tokens=256,
    temperature=0.62,
    top_p=0.95,
    top_k=16,
    repetition_penalty=1.05,
    do_sample=True
)

print(outputs[0]["generated_text"])

---

Output:

<|im_start|>system
Sen bir asistansın. Kısa ve doğru cevaplar ver.<|im_end|>
<|im_start|>user
5+1 kaç eder?<|im_end|>
<|im_start|>assistant
Adım 1: 5 ve 1 sayılarını toplamam gerekiyor.
Adım 2: 5 + 1 = 6.
Cevap: 6

Evaluation

Summary

Model Examination [optional]

[More Information Needed]