The true weight file not find? #131

Activity

1. csuhan commented on Nov 20, 2023

   

   csuhan

   on Nov 20, 2023

   Collaborator

   More actions

   It seems that you forgot to pass the llama_type param:

   def load(name, llama_dir, llama_type="7B", device="cuda" if torch.cuda.is_available() else "cpu", download_root='ckpts', max_seq_len=512, phase="finetune")
   

   https://github.com/OpenGVLab/LLaMA-Adapter/blob/b82e90bd31dc75d6fdca0a35b53ff00d1b96bc47/llama_adapter_v2_multimodal7b/llama/llama_adapter.py#L290C1-L291C26
2. fengmingfeng commented on Nov 20, 2023

   

   fengmingfeng

   on Nov 20, 2023

   Author

   More actions

   these code just download the base model,but it not provide tokenizer.model and params.json and so on!
   could you please provide these files with me.
   /path/to/llama_model_weights
   ├── 7B
   │   ├── checklist.chk
   │   ├── consolidated.00.pth
   │   └── params.json
   └── tokenizer.model

   _MODELS = {
   "BIAS-7B": "https://github.com/OpenGVLab/LLaMA-Adapter/releases/download/v.2.0.0/7fa55208379faf2dd862565284101b0e4a2a72114d6490a95e432cf9d9b6c813_BIAS-7B.pth",
   "LORA-BIAS-7B": "https://github.com/OpenGVLab/LLaMA-Adapter/releases/download/v.2.0.0/1bcbffc43484332672092e0024a8699a6eb5f558161aebf98a7c6b1db67224d1_LORA-BIAS-7B.pth",
   "CAPTION-7B": "https://github.com/OpenGVLab/LLaMA-Adapter/releases/download/v.2.0.0/5088aeb63a89746b90bcfd5cb819e1c7411b2771b267c6d131ce73e250a8abf0_CAPTION-7B.pth",
   "LORA-BIAS-7B-v21": "https://github.com/OpenGVLab/LLaMA-Adapter/releases/download/v.2.1.0/d26d107eec32127ac86ef1997cf7169de1c56a59c539fc1258c6798b969e289c_LORA-BIAS-7B-v21.pth",
   # "LORA16-7B": "",
   # "PARTIAL-7B": ""
   }

   def available_models():
   return list(_MODELS.keys())

   def load(name, llama_dir, llama_type="7B", device="cuda" if torch.cuda.is_available() else "cpu", download_root='ckpts', max_seq_len=512,
   phase="finetune"):
   if name in _MODELS:
   model_path = _download(_MODELS[name], download_root)
   elif os.path.isfile(name):
   model_path = name
   else:
   return RuntimeError(f"Model {name} not found; available models = {available_models()}"), None

   # BIAS-7B or https://xxx/sha256_BIAS-7B.pth -> 7B
   # llama_type = name.split('.')[0].split('-')[-1]
   llama_ckpt_dir = os.path.join(llama_dir, llama_type)
   llama_tokenzier_path = os.path.join(llama_dir, 'tokenizer.model')
   
   # load llama_adapter weights and model_cfg
   print(f'Loading LLaMA-Adapter from {model_path}')
   ckpt = torch.load(model_path, map_location='cpu')
   model_cfg = ckpt.get('config', {})
   
   model = LLaMA_adapter(
       llama_ckpt_dir, llama_tokenzier_path,
       max_seq_len=512, max_batch_size=1,
       clip_model='ViT-L/14',
       v_embed_dim=768, v_depth=8,
       v_num_heads=16, v_mlp_ratio=4.0,
       query_len=10, query_layer=31,
       w_bias=model_cfg.get('w_bias', False), 
       w_lora=model_cfg.get('w_lora', False), 
       lora_rank=model_cfg.get('lora_rank', 16),
       w_new_gate=model_cfg.get('w_lora', False), # for compatibility
       phase=phase)
   
3. Cheng909865905 commented on Dec 2, 2023

   

   Cheng909865905

   on Dec 2, 2023

   More actions

   你好 我也遇到同样的问题 找不到BIAS-7B 模型的相关tokenizer.model 和 params.json文件 ，请问您解决了嘛 我的q 909865905 将不甚感激
4. fengmingfeng commented on Dec 4, 2023

   

   fengmingfeng

   on Dec 4, 2023

   Author

   More actions

   你好 我也遇到同样的问题 找不到BIAS-7B 模型的相关tokenizer.model 和 params.json文件 ，请问您解决了嘛 我的q 909865905 将不甚感激

   抱歉，我也没有解决