Update README.md

Browse files

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -65,17 +65,17 @@ 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
 ```
@@ -98,38 +98,38 @@ 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).
-# Download vllm source code and install vllm
 ```
 git clone [email protected]:vllm-project/vllm.git
 VLLM_USE_PRECOMPILED=1 pip install .
 ```
-# Download dataset
 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
 Run the following under `vllm` source code root folder:
-## baseline
 ```
 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model microsoft/Phi-4-mini-instruct --batch-size 1
 ```
-## int4wo-hqq
 ```
 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model jerryzh168/phi4-mini-int4wo-hqq --batch-size 1
 ```
-# benchmark_serving
 We also benchmarked the throughput in a serving environment.
 Run the following under `vllm` source code root folder:
-## baseline
 Server:
 ```
 vllm serve microsoft/Phi-4-mini-instruct --tokenizer microsoft/Phi-4-mini-instruct -O3
@@ -140,7 +140,7 @@ Client:
 python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --tokenizer microsoft/Phi-4-mini-instruct --dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json --model microsoft/Phi-4-mini-instruct --num-prompts 1
 ```
-## int4wo-hqq
 Server:
 ```
 vllm serve jerryzh168/phi4-mini-int4wo-hqq --tokenizer microsoft/Phi-4-mini-instruct -O3

 # 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
 ```
 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).
+## Download vllm source code and install vllm
 ```
 git clone [email protected]:vllm-project/vllm.git
 VLLM_USE_PRECOMPILED=1 pip install .
 ```
+## Download dataset
 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
 Run the following under `vllm` source code root folder:
+### baseline
 ```
 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model microsoft/Phi-4-mini-instruct --batch-size 1
 ```
+### int4wo-hqq
 ```
 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model jerryzh168/phi4-mini-int4wo-hqq --batch-size 1
 ```
+## benchmark_serving
 We also benchmarked the throughput in a serving environment.
 Run the following under `vllm` source code root folder:
+### baseline
 Server:
 ```
 vllm serve microsoft/Phi-4-mini-instruct --tokenizer microsoft/Phi-4-mini-instruct -O3
 python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --tokenizer microsoft/Phi-4-mini-instruct --dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json --model microsoft/Phi-4-mini-instruct --num-prompts 1
 ```
+### int4wo-hqq
 Server:
 ```
 vllm serve jerryzh168/phi4-mini-int4wo-hqq --tokenizer microsoft/Phi-4-mini-instruct -O3