Configuration Parsing Warning:In UNKNOWN_FILENAME: "quantization_config.config_groups.group_0.format" must be a string

Model Details

This model is mxfp4 quantized version of moonshotai/Kimi-K2.6 based on intel/auto-round saved with llm_compressor format. Please follow the license of the original model.

Evaluate Results

torch               2.13.0
compressed-tensors  0.17.0
transformers        5.16.1
vllm                0.28.0
lm_eval             0.4.12
auto-round          0.16.0.dev143+g678f8f5f
Task backend BF16 MXFP4 FP8KV
hellaswag vllm 0.7752 0.7642
piqa vllm 0.8455 0.8439
mmlu vllm 0.8901 0.8882
gsm8k vllm 0.9363 0.9325
average vllm 0.86177 0.85720

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:

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.

Downloads last month
53
Safetensors
Model size
551B params
Tensor type
F32
·
BF16
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for INCModel3/Kimi-K2.6-MXFP4-FP8KV-CT-AutoRound

Quantized
(44)
this model