Ling-flash-2.0-gguf-q2ks-mixed-AutoRound

Model Details

This model is a mixed gguf q2ks format of inclusionAI/Ling-flash-2.0 generated by 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.

/llama-cli -hf Intel/Ling-flash-2.0-gguf-q2ks-mixed-AutoRound

> Write a quick sort algorithm.
Sure! Here's a simple and clear implementation of the **Quick Sort** algorithm in Python:

### ✅ Quick Sort in Python

```python
def quick_sort(arr):
    # Base case: arrays with 0 or 1 element are already sorted
    if len(arr) <= 1:
        return arr

    # Choose the pivot (here we pick the middle element)
    pivot = arr[len(arr) // 2]

    # Partition the array into three parts
    left =   [x for x in arr if x < pivot]    # Elements less than pivot
    middle = [x for x in arr if x == pivot]   # Elements equal to pivot
    right =  [x for x in arr if x > pivot]    # Elements greater than pivot

    # Recursively sort left and right, and concatenate the result
    return quick_sort(left) + middle + quick_sort(right)

# Example usage
arr = [3, 6, 8, 10, 1, 2, 1]
sorted_arr = quick_sort(arr)
print("Sorted array:", sorted_arr)
```

### 🧠 How It Works:
- **Divide and Conquer**: Pick a pivot, partition the array into elements less than, equal to, and greater than the pivot.
- Recursively apply the same to left and right partitions.
- **Not in-place** in this version (creates new lists). An in-place version is more memory-efficient.

### ⏱ Time Complexity:
- **Best/Average Case**: O(n log n)
- **Worst Case**: O(n²) — when the pivot is always the smallest or largest element (e.g., on already sorted data), but this is mitigated by choosing a good pivot (like middle, random, or median-of-three).

---

Would you like the **in-place version** (which is more efficient in memory) as well?

Generate the model

Requirement

pip install git+https://github.com/intel/auto-round.git@hengguo/fix_imatrix_bug

Here is the sample command to reproduce the model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from auto_round import AutoRound

model_name = "inclusionAI/Ling-flash-2.0"

model = AutoModelForCausalLM.from_pretrained(model_name,
                                             device_map="cpu", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
layer_config = {}
for n, m in model.named_modules():
    if n == "lm_head" or isinstance(m,torch.nn.Embedding):
        layer_config[n] = {"bits": 8}
    elif isinstance(m, torch.nn.Linear) and (not "expert" in n or "shared_experts" in n) and n != "lm_head":
        layer_config[n] = {"bits": 4}

autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, nsamples=4096, dataset="NeelNanda/pile-10k,HuggingFaceH4/ultrachat_200k", seqlen=1024)
autoround.quantize_and_save("tmp_autoround", format="gguf:q2_k_s")

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

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 github