Fix for llava models not generating text with test failures in 1.19 (h…

…uggingface#1548)
imangohari1 · Dec 10, 2024 · b32e148 · b32e148
1 parent f23bbb8
commit b32e148
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/examples/image-to-text/README.md b/examples/image-to-text/README.md
@@ -138,7 +138,7 @@ QUANT_CONFIG=./quantization_config/maxabs_measure.json python run_pipeline.py \
 
 Here is an example to quantize the model based on previous measurements for Llava-1.5-7b:
 ```bash
-QUANT_CONFIG=./quantization_config/maxabs_quant.json python run_pipeline.py \
+QUANT_CONFIG=./quantization_config/maxabs_quant_scale_format_const.json python run_pipeline.py \
     --model_name_or_path llava-hf/llava-1.5-7b-hf \
     --image_path "https://llava-vl.github.io/static/images/view.jpg" \
     --use_hpu_graphs \

diff --git a/tests/test_image_to_text_example.py b/tests/test_image_to_text_example.py
@@ -89,6 +89,8 @@ def _test_image_to_text(
                 "llava-hf/llava-v1.6-mistral-7b-hf",
                 "llava-hf/llava-v1.6-vicuna-7b-hf",
                 "llava-hf/llava-v1.6-vicuna-13b-hf",
+                "llava-hf/llava-1.5-7b-hf",
+                "llava-hf/llava-1.5-13b-hf",
             ]:
                 quant_file_path = "image-to-text/quantization_config/maxabs_quant_scale_format_const.json"