Upload README.md with huggingface_hub

README.md

@@ -7,14 +7,13 @@ This is a quantization of the [phi-4](https://huggingface.co/microsoft/phi-4).
 
 The phi-4 model is a cutting-edge open-source LLM developed using a diverse mix of synthetic datasets, curated public domain web content, and acquired academic resources, including books and Q&A datasets. This deliberate data selection ensures the training of compact yet highly capable models with an emphasis on quality and advanced reasoning. To further enhance its performance, phi-4 underwent a rigorous alignment process that included supervised fine-tuning and direct preference optimization, resulting in precise instruction adherence and robust safety measures.
 ## Evaluations
-This model provides an accuracy recovery of 99.73%. 
+This model provides an accuracy recovery of 99.68%. 
 
 | __English__   | __[phi-4](https://huggingface.co/microsoft/phi-4)__   | __[phi-4-FP8-Dynamic (this)](https://huggingface.co/cortecs/phi-4-FP8-Dynamic)__   |
 |:--------------|:------------------------------------------------------|:-----------------------------------------------------------------------------------|
 | Avg.          | 70.75                                                 | 70.7                                                                               |
 | Arc           | 68.7                                                  | 68.7                                                                               |
 | Hellaswag     | 72.8                                                  | 72.7                                                                               |
-| MMLU          | 79.46                                                 | 79.67                                                                              |
 |               |                                                       |                                                                                    |
 | __French__   | __[phi-4](https://huggingface.co/microsoft/phi-4)__   | __[phi-4-FP8-Dynamic (this)](https://huggingface.co/cortecs/phi-4-FP8-Dynamic)__   |
 | Avg.         | 68.67                                                 | 68.87                                                                              |
@@ -48,7 +47,7 @@ Install **vLLM** and
     run the [server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#openai-compatible-server):
     
 ```
-python -m vllm.entrypoints.openai.api_server --model cortecs/phi-4-FP8-Dynamic
+python -m vllm.entrypoints.openai.api_server --model cortecs/phi-4-FP8-Dynamic --max-model-len 16384
 ```
 Access the model:
 ```