Update README.md

README.md

@@ -62,21 +62,27 @@ print(f"{save_to} model:", benchmark_fn(quantized_model.generate, **inputs, max_
 
 # Model Quality
 We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate the quality of the quantized model.
-
 ```
+
 # Installing the nightly version to get most recent updates
+```
 pip install git+https://github.com/EleutherAI/lm-evaluation-harness
+```
 
 # baseline
+```
 lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size 8
+```
 
 # int4wo-hqq
+```
 lm_eval --model hf --model_args pretrained=jerryzh168/phi4-mini-int4wo-hqq --tasks hellaswag --device cuda:0 --batch_size 8
 ```
 
 `TODO: more complete eval results`
 
-| Benchmark                        |    | 
+
+| Benchmark                        |             |                   |
 |----------------------------------|-------------|-------------------|
 |                                  | Phi-4 mini-Ins | phi4-mini-int4wo | 
 | **Popular aggregated benchmark** |             |                   |
@@ -91,12 +97,13 @@ lm_eval --model hf --model_args pretrained=jerryzh168/phi4-mini-int4wo-hqq --tas
 Our int4wo is only optimized for batch size 1, so we'll only benchmark the batch size 1 performance with vllm.
 For batch size N, please see our [gemlite checkpoint](https://huggingface.co/jerryzh168/phi4-mini-int4wo-gemlite).
 
-```
 # Install latest vllm to get the most recent changes
+```
 pip install git+https://github.com/vllm-project/vllm.git
+```
 
 # Download dataset
-Download sharegpt dataset: wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
+Download sharegpt dataset: `wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json`
 
 Other datasets can be found in: https://github.com/vllm-project/vllm/tree/main/benchmarks
 # benchmark_latency