Create README.md

README.md

@@ -0,0 +1,206 @@
+---
+tags:
+- w4a16
+- int4
+- vllm
+license: apache-2.0
+license_link: https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md
+language:
+  - en
+base_model: ibm-granite/granite-3.1-2b-instruct
+library_name: transformers
+---
+
+# granite-3.1-2b-instruct-quantized.w4a16
+
+## Model Overview
+- **Model Architecture:** granite-3.1-2b-instruct
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** INT4
+  - **Activation quantization:** INT4
+- **Release Date:** 1/8/2025
+- **Version:** 1.0
+- **Model Developers:** Neural Magic
+
+Quantized version of [ibm-granite/granite-3.1-2b-instruct](https://huggingface.co/ibm-granite/granite-3.1-2b-instruct).
+It achieves an average score of xxxx on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves xxxx.
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights of [ibm-granite/granite-3.1-2b-instruct](https://huggingface.co/ibm-granite/granite-3.1-2b-instruct) to INT4 data type, ready for inference with vLLM >= 0.5.2.
+This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within transformers blocks are quantized. 
+
+## Deployment
+
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+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.w4a16"
+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])
+
+messages_list = [
+    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
+]
+
+prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
+
+outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
+
+generated_text = [output.outputs[0].text for output in outputs]
+print(generated_text)
+```
+
+vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. 
+
+
+```bash
+python quantize.py --model_path ibm-granite/granite-3.1-2b-instruct --quant_path "output_dir/granite-3.1-2b-instruct-quantized.w4a16" --calib_size 2048 --dampening_frac 0.01 --observer mse 
+```
+
+
+```python
+from datasets import load_dataset
+from transformers import AutoTokenizer
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot, apply
+import argparse
+from compressed_tensors.quantization import QuantizationScheme, QuantizationArgs, QuantizationType, QuantizationStrategy
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--model_path', type=str)
+parser.add_argument('--quant_path', type=str)
+parser.add_argument('--calib_size', type=int, default=256)
+parser.add_argument('--dampening_frac', type=float, default=0.1) 
+parser.add_argument('--observer', type=str, default="minmax")
+args = parser.parse_args()
+
+model = SparseAutoModelForCausalLM.from_pretrained(
+    args.model_path,
+    device_map="auto",
+    torch_dtype="auto",
+    use_cache=False,
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained(args.model_path)
+
+
+NUM_CALIBRATION_SAMPLES = args.calib_size
+DATASET_ID = "neuralmagic/LLM_compression_calibration"
+DATASET_SPLIT = "train"
+ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
+ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
+
+def preprocess(example):
+    concat_txt = example["instruction"] + "\n" + example["output"]
+    return {"text": concat_txt}
+
+ds = ds.map(preprocess)
+
+def tokenize(sample):
+    return tokenizer(
+        sample["text"],
+        padding=False,
+        truncation=False,
+        add_special_tokens=True,
+    )
+
+
+ds = ds.map(tokenize, remove_columns=ds.column_names)
+
+recipe = [
+    GPTQModifier(
+        targets=["Linear"],
+        ignore=["lm_head"],
+        scheme="w4a16",
+        dampening_frac=args.dampening_frac,
+        observer=args.observer,
+    )
+]
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    num_calibration_samples=args.calib_size,
+    max_seq_length=8196,
+)
+
+# Save to disk compressed.
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)
+```
+
+## 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:
+
+OpenLLM Leaderboard V1:
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic-ent/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 openllm \
+  --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.w4a16 \
+  --bs 16 \
+  --temperature 0.2 \
+  --n_samples 50 \
+  --root "." \
+  --dataset humaneval
+```
+##### Sanitization
+```
+python3 evalplus/sanitize.py \
+  humaneval/neuralmagic-ent--granite-3.1-2b-instruct-quantized.w4a16_vllm_temp_0.2
+```
+##### Evaluation
+```
+evalplus.evaluate \
+  --dataset humaneval \
+  --samples humaneval/neuralmagic-ent--granite-3.1-2b-instruct-quantized.w4a16_vllm_temp_0.2-sanitized
+```
+
+### Accuracy
+
+#### OpenLLM Leaderboard V1 evaluation scores
+
+| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic-ent/granite-3.1-2b-instruct-quantized.w4a16 |
+|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
+| ARC-Challenge (Acc-Norm, 25-shot)       | 55.63                             | 55.72                                      |
+| GSM8K (Strict-Match, 5-shot)            | 60.96                             | 54.51                                       |
+| HellaSwag (Acc-Norm, 10-shot)           | 75.21                             | 71.92                                       |
+| MMLU (Acc, 5-shot)                      | 54.38                             | 51.96                                        |
+| TruthfulQA (MC2, 0-shot)                | 55.93                             | 52.90                                        |
+| Winogrande (Acc, 5-shot)                | 69.67                             | 67.56                                        |
+| **Average Score**                       | **61.98**                         | **59.09**                                   |
+| **Recovery**                            | **100.00**                        | **95.34**                                   |
+
+#### HumanEval pass@1 scores
+| Metric                                  | ibm-granite/granite-3.1-2b-instruct             | neuralmagic-ent/granite-3.1-2b-instruct-quantized.w4a16 |
+|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
+| HumanEval Pass@1                        | 53.40                             |  50.70                                     |
+
+