From d3b5ae27b0bf47880ceedab93ba10f35c04fa1a9 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Thu, 21 Dec 2023 15:38:40 +0000 Subject: [PATCH] Fix santacoder. --- .../models/custom_modeling/flash_santacoder_modeling.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py b/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py index cd93d32a..22d03adf 100644 --- a/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py +++ b/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py @@ -71,7 +71,7 @@ def _load_multi_mqa_gptq( g_idx = weights.get_tensor(f"{prefix}.c_attn.g_idx") g_idx = g_idx.to(device=weights.device) - bits, groupsize = weights._get_gptq_params() + bits, groupsize, _ = weights._get_gptq_params() from text_generation_server.utils.layers import HAS_EXLLAMA