Instructions to use mudkip02/llama3.2-1b-mmqa-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mudkip02/llama3.2-1b-mmqa-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct") model = PeftModel.from_pretrained(base_model, "mudkip02/llama3.2-1b-mmqa-lora") - Transformers
How to use mudkip02/llama3.2-1b-mmqa-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mudkip02/llama3.2-1b-mmqa-lora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mudkip02/llama3.2-1b-mmqa-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mudkip02/llama3.2-1b-mmqa-lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mudkip02/llama3.2-1b-mmqa-lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mudkip02/llama3.2-1b-mmqa-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mudkip02/llama3.2-1b-mmqa-lora
- SGLang
How to use mudkip02/llama3.2-1b-mmqa-lora 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 "mudkip02/llama3.2-1b-mmqa-lora" \ --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": "mudkip02/llama3.2-1b-mmqa-lora", "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 "mudkip02/llama3.2-1b-mmqa-lora" \ --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": "mudkip02/llama3.2-1b-mmqa-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use mudkip02/llama3.2-1b-mmqa-lora with Docker Model Runner:
docker model run hf.co/mudkip02/llama3.2-1b-mmqa-lora
llama3.2-1b-mmqa-lora-llamafactory
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the meta_math_qa dataset. It achieves the following results on the evaluation set:
- Loss: 0.1650
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2644 | 0.0102 | 250 | 0.2924 |
| 0.2617 | 0.0203 | 500 | 0.2548 |
| 0.2452 | 0.0305 | 750 | 0.2433 |
| 0.2504 | 0.0406 | 1000 | 0.2358 |
| 0.2260 | 0.0508 | 1250 | 0.2310 |
| 0.2677 | 0.0609 | 1500 | 0.2274 |
| 0.2244 | 0.0711 | 1750 | 0.2240 |
| 0.2262 | 0.0812 | 2000 | 0.2211 |
| 0.2081 | 0.0914 | 2250 | 0.2180 |
| 0.2281 | 0.1015 | 2500 | 0.2152 |
| 0.2049 | 0.1117 | 2750 | 0.2142 |
| 0.2185 | 0.1218 | 3000 | 0.2136 |
| 0.1952 | 0.1320 | 3250 | 0.2120 |
| 0.2221 | 0.1421 | 3500 | 0.2120 |
| 0.2139 | 0.1523 | 3750 | 0.2089 |
| 0.1953 | 0.1624 | 4000 | 0.2067 |
| 0.2038 | 0.1726 | 4250 | 0.2059 |
| 0.2062 | 0.1827 | 4500 | 0.2050 |
| 0.2190 | 0.1929 | 4750 | 0.2035 |
| 0.2054 | 0.2030 | 5000 | 0.2035 |
| 0.2237 | 0.2132 | 5250 | 0.2030 |
| 0.2152 | 0.2234 | 5500 | 0.2023 |
| 0.2011 | 0.2335 | 5750 | 0.2010 |
| 0.2099 | 0.2437 | 6000 | 0.1999 |
| 0.1972 | 0.2538 | 6250 | 0.1998 |
| 0.2041 | 0.2640 | 6500 | 0.1992 |
| 0.1894 | 0.2741 | 6750 | 0.1987 |
| 0.1903 | 0.2843 | 7000 | 0.1976 |
| 0.1906 | 0.2944 | 7250 | 0.1970 |
| 0.2041 | 0.3046 | 7500 | 0.1957 |
| 0.1954 | 0.3147 | 7750 | 0.1959 |
| 0.1977 | 0.3249 | 8000 | 0.1954 |
| 0.1814 | 0.3350 | 8250 | 0.1946 |
| 0.1840 | 0.3452 | 8500 | 0.1945 |
| 0.1937 | 0.3553 | 8750 | 0.1935 |
| 0.1996 | 0.3655 | 9000 | 0.1923 |
| 0.2193 | 0.3756 | 9250 | 0.1928 |
| 0.2102 | 0.3858 | 9500 | 0.1930 |
| 0.1998 | 0.3959 | 9750 | 0.1924 |
| 0.2047 | 0.4061 | 10000 | 0.1915 |
| 0.1897 | 0.4162 | 10250 | 0.1911 |
| 0.1716 | 0.4264 | 10500 | 0.1907 |
| 0.1832 | 0.4365 | 10750 | 0.1908 |
| 0.1871 | 0.4467 | 11000 | 0.1900 |
| 0.1855 | 0.4569 | 11250 | 0.1900 |
| 0.1786 | 0.4670 | 11500 | 0.1893 |
| 0.1919 | 0.4772 | 11750 | 0.1889 |
| 0.1930 | 0.4873 | 12000 | 0.1889 |
| 0.1908 | 0.4975 | 12250 | 0.1886 |
| 0.1934 | 0.5076 | 12500 | 0.1875 |
| 0.1867 | 0.5178 | 12750 | 0.1877 |
| 0.1803 | 0.5279 | 13000 | 0.1873 |
| 0.1997 | 0.5381 | 13250 | 0.1875 |
| 0.1838 | 0.5482 | 13500 | 0.1868 |
| 0.1843 | 0.5584 | 13750 | 0.1862 |
| 0.1825 | 0.5685 | 14000 | 0.1860 |
| 0.1781 | 0.5787 | 14250 | 0.1861 |
| 0.1729 | 0.5888 | 14500 | 0.1851 |
| 0.1951 | 0.5990 | 14750 | 0.1850 |
| 0.1750 | 0.6091 | 15000 | 0.1844 |
| 0.1676 | 0.6193 | 15250 | 0.1840 |
| 0.1882 | 0.6294 | 15500 | 0.1839 |
| 0.1525 | 0.6396 | 15750 | 0.1837 |
| 0.1685 | 0.6497 | 16000 | 0.1833 |
| 0.1799 | 0.6599 | 16250 | 0.1832 |
| 0.1970 | 0.6701 | 16500 | 0.1823 |
| 0.1802 | 0.6802 | 16750 | 0.1821 |
| 0.1761 | 0.6904 | 17000 | 0.1812 |
| 0.1772 | 0.7005 | 17250 | 0.1814 |
| 0.1750 | 0.7107 | 17500 | 0.1816 |
| 0.1831 | 0.7208 | 17750 | 0.1808 |
| 0.1782 | 0.7310 | 18000 | 0.1806 |
| 0.2073 | 0.7411 | 18250 | 0.1807 |
| 0.1899 | 0.7513 | 18500 | 0.1803 |
| 0.1909 | 0.7614 | 18750 | 0.1801 |
| 0.1822 | 0.7716 | 19000 | 0.1790 |
| 0.1843 | 0.7817 | 19250 | 0.1793 |
| 0.1749 | 0.7919 | 19500 | 0.1793 |
| 0.1827 | 0.8020 | 19750 | 0.1789 |
| 0.1611 | 0.8122 | 20000 | 0.1785 |
| 0.1840 | 0.8223 | 20250 | 0.1785 |
| 0.1745 | 0.8325 | 20500 | 0.1786 |
| 0.1722 | 0.8426 | 20750 | 0.1782 |
| 0.1792 | 0.8528 | 21000 | 0.1776 |
| 0.1758 | 0.8629 | 21250 | 0.1777 |
| 0.1736 | 0.8731 | 21500 | 0.1777 |
| 0.1670 | 0.8832 | 21750 | 0.1768 |
| 0.1651 | 0.8934 | 22000 | 0.1769 |
| 0.1744 | 0.9036 | 22250 | 0.1767 |
| 0.1879 | 0.9137 | 22500 | 0.1767 |
| 0.1847 | 0.9239 | 22750 | 0.1760 |
| 0.1968 | 0.9340 | 23000 | 0.1763 |
| 0.1803 | 0.9442 | 23250 | 0.1756 |
| 0.1550 | 0.9543 | 23500 | 0.1751 |
| 0.1782 | 0.9645 | 23750 | 0.1755 |
| 0.1715 | 0.9746 | 24000 | 0.1751 |
| 0.1837 | 0.9848 | 24250 | 0.1750 |
| 0.1851 | 0.9949 | 24500 | 0.1748 |
| 0.1622 | 1.0051 | 24750 | 0.1754 |
| 0.1524 | 1.0152 | 25000 | 0.1750 |
| 0.1570 | 1.0254 | 25250 | 0.1747 |
| 0.1461 | 1.0355 | 25500 | 0.1747 |
| 0.1568 | 1.0457 | 25750 | 0.1745 |
| 0.1620 | 1.0558 | 26000 | 0.1744 |
| 0.1515 | 1.0660 | 26250 | 0.1744 |
| 0.1518 | 1.0761 | 26500 | 0.1739 |
| 0.1606 | 1.0863 | 26750 | 0.1730 |
| 0.1505 | 1.0964 | 27000 | 0.1741 |
| 0.1492 | 1.1066 | 27250 | 0.1736 |
| 0.1482 | 1.1168 | 27500 | 0.1737 |
| 0.1594 | 1.1269 | 27750 | 0.1731 |
| 0.1563 | 1.1371 | 28000 | 0.1729 |
| 0.1450 | 1.1472 | 28250 | 0.1726 |
| 0.1554 | 1.1574 | 28500 | 0.1726 |
| 0.1626 | 1.1675 | 28750 | 0.1725 |
| 0.1604 | 1.1777 | 29000 | 0.1723 |
| 0.1386 | 1.1878 | 29250 | 0.1722 |
| 0.1573 | 1.1980 | 29500 | 0.1716 |
| 0.1504 | 1.2081 | 29750 | 0.1717 |
| 0.1577 | 1.2183 | 30000 | 0.1712 |
| 0.1522 | 1.2284 | 30250 | 0.1712 |
| 0.1407 | 1.2386 | 30500 | 0.1711 |
| 0.1384 | 1.2487 | 30750 | 0.1709 |
| 0.1655 | 1.2589 | 31000 | 0.1713 |
| 0.1504 | 1.2690 | 31250 | 0.1704 |
| 0.1523 | 1.2792 | 31500 | 0.1703 |
| 0.1527 | 1.2893 | 31750 | 0.1700 |
| 0.1486 | 1.2995 | 32000 | 0.1697 |
| 0.1493 | 1.3096 | 32250 | 0.1698 |
| 0.1452 | 1.3198 | 32500 | 0.1695 |
| 0.1429 | 1.3299 | 32750 | 0.1693 |
| 0.1561 | 1.3401 | 33000 | 0.1695 |
| 0.1559 | 1.3503 | 33250 | 0.1691 |
| 0.1518 | 1.3604 | 33500 | 0.1693 |
| 0.1637 | 1.3706 | 33750 | 0.1692 |
| 0.1527 | 1.3807 | 34000 | 0.1690 |
| 0.1640 | 1.3909 | 34250 | 0.1688 |
| 0.1416 | 1.4010 | 34500 | 0.1689 |
| 0.1524 | 1.4112 | 34750 | 0.1686 |
| 0.1558 | 1.4213 | 35000 | 0.1683 |
| 0.1452 | 1.4315 | 35250 | 0.1680 |
| 0.1529 | 1.4416 | 35500 | 0.1678 |
| 0.1470 | 1.4518 | 35750 | 0.1678 |
| 0.1589 | 1.4619 | 36000 | 0.1679 |
| 0.1555 | 1.4721 | 36250 | 0.1676 |
| 0.1489 | 1.4822 | 36500 | 0.1676 |
| 0.1578 | 1.4924 | 36750 | 0.1672 |
| 0.1521 | 1.5025 | 37000 | 0.1673 |
| 0.1594 | 1.5127 | 37250 | 0.1674 |
| 0.1359 | 1.5228 | 37500 | 0.1670 |
| 0.1415 | 1.5330 | 37750 | 0.1669 |
| 0.1531 | 1.5431 | 38000 | 0.1669 |
| 0.1527 | 1.5533 | 38250 | 0.1670 |
| 0.1495 | 1.5635 | 38500 | 0.1667 |
| 0.1525 | 1.5736 | 38750 | 0.1667 |
| 0.1528 | 1.5838 | 39000 | 0.1666 |
| 0.1657 | 1.5939 | 39250 | 0.1666 |
| 0.1424 | 1.6041 | 39500 | 0.1666 |
| 0.1351 | 1.6142 | 39750 | 0.1665 |
| 0.1611 | 1.6244 | 40000 | 0.1664 |
| 0.1379 | 1.6345 | 40250 | 0.1665 |
| 0.1547 | 1.6447 | 40500 | 0.1664 |
| 0.1593 | 1.6548 | 40750 | 0.1664 |
| 0.1524 | 1.6650 | 41000 | 0.1661 |
| 0.1569 | 1.6751 | 41250 | 0.1662 |
| 0.1640 | 1.6853 | 41500 | 0.1659 |
| 0.1528 | 1.6954 | 41750 | 0.1659 |
| 0.1543 | 1.7056 | 42000 | 0.1658 |
| 0.1701 | 1.7157 | 42250 | 0.1657 |
| 0.1483 | 1.7259 | 42500 | 0.1656 |
| 0.1491 | 1.7360 | 42750 | 0.1655 |
| 0.1456 | 1.7462 | 43000 | 0.1654 |
| 0.1386 | 1.7563 | 43250 | 0.1655 |
| 0.1743 | 1.7665 | 43500 | 0.1654 |
| 0.1528 | 1.7766 | 43750 | 0.1654 |
| 0.1653 | 1.7868 | 44000 | 0.1654 |
| 0.1550 | 1.7970 | 44250 | 0.1654 |
| 0.1466 | 1.8071 | 44500 | 0.1653 |
| 0.1488 | 1.8173 | 44750 | 0.1653 |
| 0.1385 | 1.8274 | 45000 | 0.1652 |
| 0.1517 | 1.8376 | 45250 | 0.1652 |
| 0.1508 | 1.8477 | 45500 | 0.1652 |
| 0.1465 | 1.8579 | 45750 | 0.1652 |
| 0.1598 | 1.8680 | 46000 | 0.1652 |
| 0.1478 | 1.8782 | 46250 | 0.1652 |
| 0.1442 | 1.8883 | 46500 | 0.1652 |
| 0.1510 | 1.8985 | 46750 | 0.1652 |
| 0.1490 | 1.9086 | 47000 | 0.1651 |
| 0.1473 | 1.9188 | 47250 | 0.1651 |
| 0.1514 | 1.9289 | 47500 | 0.1651 |
| 0.1492 | 1.9391 | 47750 | 0.1652 |
| 0.1590 | 1.9492 | 48000 | 0.1651 |
| 0.1612 | 1.9594 | 48250 | 0.1651 |
| 0.1488 | 1.9695 | 48500 | 0.1652 |
| 0.1521 | 1.9797 | 48750 | 0.1652 |
| 0.1554 | 1.9898 | 49000 | 0.1651 |
| 0.1497 | 2.0 | 49250 | 0.1650 |
Framework versions
- PEFT 0.19.1
- Transformers 5.6.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 7
Model tree for mudkip02/llama3.2-1b-mmqa-lora
Base model
meta-llama/Llama-3.2-1B-Instruct