s3nh

/

Baichuan-13B-Instruction-GPTQ

like 4

Traceback (most recent call last):
File "F:\AI-RWKV\oobabooga_windows\text-generation-webui\server.py", line 68, in load_model_wrapper
shared.model, shared.tokenizer = load_model(shared.model_name, loader)
File "F:\AI-RWKV\oobabooga_windows\text-generation-webui\modules\models.py", line 78, in load_model
output = load_func_maploader
File "F:\AI-RWKV\oobabooga_windows\text-generation-webui\modules\models.py", line 305, in ExLlama_HF_loader
return ExllamaHF.from_pretrained(model_name)
File "F:\AI-RWKV\oobabooga_windows\text-generation-webui\modules\exllama_hf.py", line 116, in from_pretrained
return ExllamaHF(config)
File "F:\AI-RWKV\oobabooga_windows\text-generation-webui\modules\exllama_hf.py", line 31, in init
self.ex_model = ExLlama(self.ex_config)
File "F:\AI-RWKV\oobabooga_windows\installer_files\env\lib\site-packages\exllama\model.py", line 772, in init
layer = ExLlamaDecoderLayer(self.config, tensors, f"model.layers.{i}", i, sin, cos)
File "F:\AI-RWKV\oobabooga_windows\installer_files\env\lib\site-packages\exllama\model.py", line 451, in init
self.self_attn = ExLlamaAttention(self.config, tensors, key + ".self_attn", sin, cos, self.index)
File "F:\AI-RWKV\oobabooga_windows\installer_files\env\lib\site-packages\exllama\model.py", line 289, in init
self.q_proj = Ex4bitLinear(config, self.config.hidden_size, self.config.num_attention_heads * self.config.head_dim, False, tensors, key + ".q_proj")
File "F:\AI-RWKV\oobabooga_windows\installer_files\env\lib\site-packages\exllama\model.py", line 126, in init
self.qweight = tensors[key + ".qweight"]
KeyError: 'model.layers.0.self_attn.q_proj.qweight'