Update README.md

README.md

@@ -43,7 +43,7 @@ from transformers import AutoTokenizer
 from vllm import LLM, SamplingParams
 
 max_model_len, tp_size = 4096, 1
-model_name = "neuralmagic-ent/granite-3.1-2b-instruct-quantized.w8a8"
+model_name = "neuralmagic/granite-3.1-2b-instruct-quantized.w8a8"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True)
 sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
@@ -66,7 +66,9 @@ vLLM also supports OpenAI-compatible serving. See the [documentation](https://do
 
 This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. 
 
-
+<details>
+  <summary>Model Creation Code</summary>
+  
 ```bash
 python quantize.py --model_path ibm-granite/granite-3.1-2b-instruct --quant_path "output_dir/granite-3.1-2b-instruct-quantized.w8a8" --calib_size 2048 --dampening_frac 0.01 --observer mse
 ```
@@ -151,16 +153,20 @@ oneshot(
 model.save_pretrained(quant_path, save_compressed=True)
 tokenizer.save_pretrained(quant_path)
 ```
+</details>
 
 ## Evaluation
 
-The model was evaluated on OpenLLM Leaderboard [V1](https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard) and on [HumanEval](https://github.com/neuralmagic/evalplus), using the following commands:
+The model was evaluated on OpenLLM Leaderboard [V1](https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard), OpenLLM Leaderboard [V2](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/) and on [HumanEval](https://github.com/neuralmagic/evalplus), using the following commands:
 
+<details>
+<summary>Evaluation Commands</summary>
+  
 OpenLLM Leaderboard V1:
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic-ent/granite-3.1-2b-instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
+  --model_args pretrained="neuralmagic/granite-3.1-2b-instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
   --tasks openllm \
   --write_out \
   --batch_size auto \
@@ -168,11 +174,23 @@ lm_eval \
   --show_config
 ```
 
+OpenLLM Leaderboard V2:
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/granite-3.1-2b-instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
+  --tasks leaderboard \
+  --write_out \
+  --batch_size auto \
+  --output_path output_dir \
+  --show_config
+```
+
 #### HumanEval
 ##### Generation
 ```
 python3 codegen/generate.py \
-  --model neuralmagic-ent/granite-3.1-2b-instruct-quantized.w8a8 \
+  --model neuralmagic/granite-3.1-2b-instruct-quantized.w8a8 \
   --bs 16 \
   --temperature 0.2 \
   --n_samples 50 \
@@ -182,20 +200,21 @@ python3 codegen/generate.py \
 ##### Sanitization
 ```
 python3 evalplus/sanitize.py \
-  humaneval/neuralmagic-ent--granite-3.1-2b-instruct-quantized.w8a8_vllm_temp_0.2
+  humaneval/neuralmagic--granite-3.1-2b-instruct-quantized.w8a8_vllm_temp_0.2
 ```
 ##### Evaluation
 ```
 evalplus.evaluate \
   --dataset humaneval \
-  --samples humaneval/neuralmagic-ent--granite-3.1-2b-instruct-quantized.w8a8_vllm_temp_0.2-sanitized
+  --samples humaneval/neuralmagic--granite-3.1-2b-instruct-quantized.w8a8_vllm_temp_0.2-sanitized
 ```
+</details>
 
 ### Accuracy
 
 #### OpenLLM Leaderboard V1 evaluation scores
 
-| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic-ent/granite-3.1-2b-instruct-quantized.w8a8 |
+| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic/granite-3.1-2b-instruct-quantized.w8a8 |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
 | ARC-Challenge (Acc-Norm, 25-shot)       | 55.63                             | 55.12                                       |
 | GSM8K (Strict-Match, 5-shot)            | 60.96                             | 60.58                                       |
@@ -207,7 +226,7 @@ evalplus.evaluate \
 | **Recovery**                            | **100.00**                        | **99.51**                                   |
 
 #### OpenLLM Leaderboard V2 evaluation scores
-| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic-ent/granite-3.1-2b-instruct-quantized.w8a8 |
+| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic/granite-3.1-2b-instruct-quantized.w8a8 |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
 | IFEval (Inst Level Strict Acc, 0-shot)| 67.99                           | 67.03                                          |
 | BBH (Acc-Norm, 3-shot)            | 44.11                             | 43.53                                        |
@@ -219,7 +238,7 @@ evalplus.evaluate \
 | **Recovery**                      | **100.00**                         | **98.40**                                    |
 
 #### HumanEval pass@1 scores
-| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic-ent/granite-3.1-2b-instruct-quantized.w8a8 |
+| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic/granite-3.1-2b-instruct-quantized.w8a8 |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
 | HumanEval Pass@1                        | 53.40                             | 54.9                                      |
 
@@ -230,6 +249,16 @@ evalplus.evaluate \
 This model achieves up to 1.4x speedup in single-stream deployment and up to 1.1x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
 The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.6.6.post1, and [GuideLLM](https://github.com/neuralmagic/guidellm).
 
+<details>
+<summary>Benchmarking Command</summary>
+
+```
+guidellm --model neuralmagic/granite-3.1-2b-instruct-quantized.w8a8 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_server
+```
+
+</details>
+
+
 ### Single-stream performance (measured with vLLM version 0.6.6.post1)
 <table>
   <tr>