Create README.md

README.md

@@ -0,0 +1,241 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+base_model:
+- nvidia/NVIDIA-Nemotron-Nano-9B-v2
+tags:
+- neuralmagic
+- redhat
+- llmcompressor
+- quantized
+- INT4
+---
+
+# NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16
+
+## Model Overview
+- **Model Architecture:** NemotronHForCausalLM
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** INT4
+- **Release Date:** 10/22/2025
+- **Version:** 1.0
+- **Model Developers:** RedHat (Neural Magic)
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights of [NVIDIA-Nemotron-Nano-9B-v2](https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2) to INT4 data type.
+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.
+Weights are quantized using a symmetric per-group scheme, with group size 64.
+The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library.
+
+
+## Deployment
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model_id = "RedHatAI/NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16"
+number_gpus = 1
+sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)
+
+messages = [
+    {"role": "user", "content": prompt}
+]
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]
+
+prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+
+llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
+
+outputs = llm.generate(prompts, sampling_params)
+
+generated_text = outputs[0].outputs[0].text
+print(generated_text)
+```
+
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+<details>
+  <summary>Creation details</summary>
+  This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. 
+
+
+```python
+from compressed_tensors.quantization import QuantizationScheme, QuantizationArgs, QuantizationType, QuantizationStrategy
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.transformers import oneshot
+from transformers import AutoModelForCausalLM, AutoTokenizer
+  
+# Load model
+model_stub = "nvidia/NVIDIA-Nemotron-Nano-9B-v2"
+model_name = model_stub.split("/")[-1]
+
+num_samples = 1024
+max_seq_len = 8192
+
+model = AutoModelForCausalLM.from_pretrained(model_stub)
+
+tokenizer = AutoTokenizer.from_pretrained(model_stub)
+
+def preprocess_fn(example):
+    return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
+  
+ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
+ds = ds.map(preprocess_fn)
+
+# Configure the quantization algorithm and scheme
+quant_scheme = QuantizationScheme(
+    targets=["Linear"],
+    weights=QuantizationArgs(
+        num_bits=4,
+        type=QuantizationType.INT,
+        symmetric=True,
+        group_size=64,
+        strategy=QuantizationStrategy.GROUP,
+        observer="mse",
+        actorder="weight"
+    ),
+    input_activations=None,
+    output_activations=None,
+)
+
+recipe = [
+    GPTQModifier(
+        ignore=["lm_head", "NemotronHMamba2Mixer"],
+        dampening_frac=0.07,
+        config_groups={"group_0": quant_scheme},
+    )
+]
+
+# Apply quantization
+oneshot(
+    model=model,
+    dataset=ds, 
+    recipe=recipe,
+    max_seq_length=max_seq_len,
+    num_calibration_samples=num_samples,
+)
+
+# Save to disk in compressed-tensors format
+save_path = model_name + "-quantized.w4a16"
+model.save_pretrained(save_path)
+tokenizer.save_pretrained(save_path)
+print(f"Model and tokenizer saved to: {save_path}")
+  ```
+</details>
+ 
+
+
+## Evaluation
+
+The model was evaluated on the set of popular reasoning tasks AIME25, Math-500, and GPQA-Diamond, using [lighteval](https://github.com/huggingface/lighteval) `v0.11.1.dev0`.
+[vLLM](https://docs.vllm.ai/en/stable/) `v0.11.1rc2.dev191+g80e945298.precompiled` was used as the inference engine for all evaluations.
+
+<details>
+  <summary>Evaluation details</summary>
+
+  **lighteval**
+  
+  lighteval_model_arguments.yaml
+  ```yaml
+  model_parameters:
+    model_name: "hosted_vllm/RedHatAI/NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16"
+    base_url: "http://0.0.0.0:8000/v1"
+    generation_parameters:
+      temperature: 0.6
+      min_p: 0.0
+      max_new_tokens: 65536
+      top_p: 0.95
+      seed: 0
+  ```
+
+  ```
+  lighteval endpoint litellm lighteval_model_arguments.yaml \
+      "lighteval|aime25|0,lighteval|math_500|0,lighteval|gpqa:diamond|0" \
+      --output-dir $OUTPUT_DIR \
+      --save-details
+  ```
+
+  ```
+  vllm serve RedHatAI/NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16 \
+    --trust-remote-code \
+    --mamba_ssm_cache_dtype float32 \
+    -tp 1 \
+    --port 8000 \
+    --gpu-memory-utilization 0.9
+  ```
+
+</details>
+
+### Accuracy
+
+<table>
+  <tr>
+   <th>Category
+   </th>
+   <th>Benchmark
+   </th>
+   <th>NVIDIA-Nemotron-Nano-9B-v2
+   </th>
+   <th>NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16<br>(this model)
+   </th>
+   <th>Recovery
+   </th>
+  </tr>
+  <tr>
+   <td rowspan="6" ><strong>Reasoning<br>(generation)</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>AIME 2025
+   </td>
+   <td>61.33
+   </td>
+   <td>58.00
+   </td>
+   <td>94.6%
+   </td>
+  </tr>
+  <tr>
+   <td>GPQA diamond
+   </td>
+   <td>56.26
+   </td>
+   <td>56.16
+   </td>
+   <td>99.8%
+   </td>
+  </tr>
+  <tr>
+   <td>Math-lvl-5
+   </td>
+   <td>96.08
+   </td>
+   <td>96.16
+   </td>
+   <td>100.0%
+   </td>
+  </tr>
+  <tr>
+   <td>Average Score
+   </td>
+   <td>71.22
+   </td>
+   <td>70.11
+   </td>
+   <td>98.44%
+   </td>
+  </tr>
+</table>