diff --git a/python/sglang/srt/models/llama2.py b/python/sglang/srt/models/llama2.py index 5f728c5a8..c5690838b 100644 --- a/python/sglang/srt/models/llama2.py +++ b/python/sglang/srt/models/llama2.py @@ -303,6 +303,8 @@ class LlamaForCausalLM(nn.Module): # Skip loading extra bias for GPTQ models. if name.endswith(".bias") and name not in params_dict: continue + if name.startswith("model.vision_tower") and name not in params_dict: + continue param = params_dict[name] weight_loader = param.weight_loader weight_loader(param, loaded_weight, shard_id) @@ -311,6 +313,8 @@ class LlamaForCausalLM(nn.Module): # Skip loading extra bias for GPTQ models. if name.endswith(".bias") and name not in params_dict: continue + if name.startswith("model.vision_tower") and name not in params_dict: + continue param = params_dict[name] weight_loader = getattr(param, "weight_loader", default_weight_loader) weight_loader(param, loaded_weight)