The true weight file not find?

[fengmingfeng]

when I run the code ".pytho demo.py", the weight not same as the provided one

100%|███████████████████████████████████████| 241M/241M [01:38<00:00, 2.55MiB/s]
Loading LLaMA-Adapter from ckpts/7fa55208379faf2dd862565284101b0e4a2a72114d6490a95e432cf9d9b6c813_BIAS-7B.pth
Traceback (most recent call last):
File "demo.py", line 11, in
model, preprocess = llama.load("BIAS-7B", llama_dir, device)
File "/root/autodl-tmp/LLaMA-Adapter/llama_adapter_v2_multimodal7b/llama/llama_adapter.py", line 309, in load
model = LLaMA_adapter(
File "/root/autodl-tmp/LLaMA-Adapter/llama_adapter_v2_multimodal7b/llama/llama_adapter.py", line 30, in init
with open(os.path.join(llama_ckpt_dir, "params.json"), "r") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/path/to/LLaMA/cpu/params.json'

[csuhan]

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

[fengmingfeng]

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)

[Cheng909865905]

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

[fengmingfeng]

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