Added evaluation metrics and usage example

README.md

@@ -0,0 +1,103 @@
+---
+license: gemma
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- int4
+- vllm
+- llmcompressor
+base_model: google/gemma-3-12b-it
+---
+
+# gemma-3-12b-it-GPTQ-4b-128g
+
+## Model Overview
+
+This model was obtained by quantizing the weights of [gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it) 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 `language_model` transformers blocks are quantized. Vision model and multimodal projection are kept in original precision. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization.
+
+Model checkpoint is saved in [compressed_tensors](https://github.com/neuralmagic/compressed-tensors) format.
+
+## Evaluation 
+
+This model was evaluated on the OpenLLM v1 benchmarks. Model outputs were generated with the `vLLM` engine.
+
+| Model                      |  ArcC  |  GSM8k | Hellaswag |  MMLU  | TruthfulQA-mc2 | Winogrande | Average | Recovery |
+|----------------------------|:------:|:------:|:---------:|:------:|:--------------:|:----------:|:-------:|:--------:|
+| gemma-3-12b-it             | 0.7125 | 0.8719 | 0.8377 | 0.7230 | 0.5798 | 0.7893 | 0.7524 | 1.0000 |
+| gemma-3-12b-it-INT4 (this) | 0.6988 | 0.8643 | 0.8254 | 0.7078 | 0.5638 | 0.7830 | 0.7405 | 0.9842 |
+
+## Reproduction
+
+The results were obtained using the following commands:
+
+```bash
+MODEL=ISTA-DASLab/gemma-3-12b-it-GPTQ-4b-128g
+MODEL_ARGS="pretrained=$MODEL,max_model_len=4096,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.80"
+
+lm_eval \
+  --model vllm \
+  --model_args $MODEL_ARGS \
+  --tasks openllm \
+  --batch_size auto
+```
+
+
+## Usage 
+
+* To use the model in `transformers` update the package to stable release of Gemma3:
+  
+  `pip install git+https://github.com/huggingface/[email protected]`
+* To use the model in `vLLM` update the package to version after this [PR](https://github.com/vllm-project/vllm/pull/14660/files).
+
+And example of inference via transformers is provided below:
+
+```python
+# pip install accelerate
+
+from transformers import AutoProcessor, Gemma3ForConditionalGeneration
+from PIL import Image
+import requests
+import torch
+
+model_id = "ISTA-DASLab/gemma-3-12b-it-GPTQ-4b-128g"
+
+model = Gemma3ForConditionalGeneration.from_pretrained(
+    model_id, device_map="auto"
+).eval()
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+messages = [
+    {
+        "role": "system",
+        "content": [{"type": "text", "text": "You are a helpful assistant."}]
+    },
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+            {"type": "text", "text": "Describe this image in detail."}
+        ]
+    }
+]
+
+inputs = processor.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=True,
+    return_dict=True, return_tensors="pt"
+).to(model.device, dtype=torch.bfloat16)
+
+input_len = inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+
+decoded = processor.decode(generation, skip_special_tokens=True)
+print(decoded)
+
+# **Overall Impression:** The image is a close-up shot of a vibrant garden scene, 
+# focusing on a cluster of pink cosmos flowers and a busy bumblebee. 
+# It has a slightly soft, natural feel, likely captured in daylight.
+```