Description
SafetensorError Traceback (most recent call last)
Cell In[2], line 11
7 # MODEL_PATH = '/home/quang/working/LLMs/oobabooga_linux/text-generation-webui/models/TheBloke_Wizard-Vicuna-7B-Uncensored-GPTQ'
8 # CHECKPOINT_PATH = '/home/quang/working/LLMs/oobabooga_linux/text-generation-webui/models/TheBloke_Wizard-Vicuna-7B-Uncensored-GPTQ/Wizard-Vicuna-7B-Uncensored-GPTQ-4bit-128g.no-act-order.safetensors'
10 DEVICE = torch.device('cuda:0')
---> 11 model, tokenizer = load_model_main(MODEL_PATH, CHECKPOINT_PATH, DEVICE)
File /mnt/c/Users/nlave/Maestria/Tesis/generativeAgent_LLM/server/model.py:56, in load_model_main(model_para, checkpoint_para, device)
55 def load_model_main(model_para, checkpoint_para, device):
---> 56 model = load_quant(model_para, checkpoint_para, 4, 128)
57 model.to(device)
58 tokenizer = AutoTokenizer.from_pretrained(model_para)
File /mnt/c/Users/nlave/Maestria/Tesis/generativeAgent_LLM/server/model.py:47, in load_quant(model, checkpoint, wbits, groupsize)
45 if checkpoint.endswith('.safetensors'):
46 from safetensors.torch import load_file as safe_load
---> 47 model.load_state_dict(safe_load(checkpoint))
48 else:
49 model.load_state_dict(torch.load(checkpoint))
File /mnt/c/Users/nlave/Maestria/Tesis/generativeAgent_LLM/env/lib/python3.10/site-packages/safetensors/torch.py:308, in load_file(filename, device)
285 """
286 Loads a safetensors file into torch format.
287
(...)
305 ```
306 """
307 result = {}
--> 308 with safe_open(filename, framework="pt", device=device) as f:
309 for k in f.keys():
310 result[k] = f.get_tensor(k)
SafetensorError: Error while deserializing header: HeaderTooLarge