File size: 4,842 Bytes
abd6627 62deed9 abd6627 40f2701 abd6627 7fde3a2 abd6627 40f2701 abd6627 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
---
base_model:
- Qwen/Qwen3-Coder-30B-A3B-Instruct
datasets:
- codeparrot/github-code-clean
pipeline_tag: text-generation
---
## Model Details
This model is a gguf q4km format of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. Embedding layer and lm-head layer are fallback to 8 bits and non expert layers are fallback to 4 bits. Please refer to Section `Generate the model` for more details.
Please follow the license of the original model.
## How To Use
Llamacpp inference
~~~bash
/llama-cli -hf Intel/Qwen3-Coder-30B-A3B-Instruct-gguf-q4km-AutoRound
~~~
~~~bash
> Write a quick sort algorithm.
Here's a quick sort algorithm implementation in Python:
```python
def quicksort(arr, low, high):
"""
Quick sort implementation
arr: array to be sorted
low: starting index
high: ending index
"""
if low < high:
# Partition the array and get pivot index
pivot_index = partition(arr, low, high)
# Recursively sort elements before and after partition
quicksort(arr, low, pivot_index - 1)
quicksort(arr, pivot_index + 1, high)
def partition(arr, low, high):
"""
Partition function using last element as pivot
"""
# Choose the rightmost element as pivot
pivot = arr[high]
# Index of smaller element (indicates right position of pivot)
i = low - 1
for j in range(low, high):
# If current element is smaller than or equal to pivot
if arr[j] <= pivot:
i += 1
arr[i], arr[j] = arr[j], arr[i] # Swap elements
# Place pivot in its correct position
arr[i + 1], arr[high] = arr[high], arr[i + 1]
return i + 1
# Wrapper function for easier use
def quick_sort(arr):
if len(arr) <= 1:
return arr
quicksort(arr, 0, len(arr) - 1)
return arr
# Example usage
if __name__ == "__main__":
# Test the algorithm
test_array = [64, 34, 25, 12, 22, 11, 90]
print("Original array:", test_array)
sorted_array = quick_sort(test_array.copy())
print("Sorted array:", sorted_array)
# Test with edge cases
print("Empty array:", quick_sort([]))
print("Single element:", quick_sort([42]))
print("Already sorted:", quick_sort([1, 2, 3, 4, 5]))
print("Reverse sorted:", quick_sort([5, 4, 3, 2, 1]))
```
**How it works:**
1. **Choose a pivot**: Select an element from the array (here we use the last element)
2. **Partition**: Rearrange the array so that:
- Elements smaller than the pivot go to the left
- Elements greater than the pivot go to the right
3. **Recursively sort**: Apply the same process to the sub-arrays on both sides of the pivot
**Time Complexity:**
- Best/Average case: O(n log n)
- Worst case: O(n²) - when pivot is always the smallest or largest element
**Space Complexity:** O(log n) - due to recursion stack
**Key Features:**
- In-place sorting (modifies original array)
- Not stable (doesn't preserve relative order of equal elements)
- Efficient for large datasets
- Good average performance
The algorithm handles edge cases like empty arrays, single elements, and already sorted arrays.
~~~
### Generate the model
Here is the sample command to reproduce the model
```bash
auto_round --format gguf:q4_k_m --iters 0 --nsamples 512 --dataset github-code-clean --model Qwen/Qwen3-Coder-30B-A3B-Instruct/ --output_dir tmp_autoround
```
## Ethical Considerations and Limitations
The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Therefore, before deploying any applications of the model, developers should perform safety testing.
## Caveats and Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Here are a couple of useful links to learn more about Intel's AI software:
- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## Cite
@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round) |