Could you please provide these weight with me?
fengmingfeng opened this issue · comments
/path/to/llama_model_weights
├── 7B
│ ├── checklist.chk
│ ├── consolidated.00.pth
│ └── params.json
└── tokenizer.model
I just want to run the fineturn code.
import cv2
import llama
import torch
from PIL import Image
device = "cuda" if torch.cuda.is_available() else "cpu"
llama_dir = "/path/to/LLaMA/"
choose from BIAS-7B, LORA-BIAS-7B, LORA-BIAS-7B-v21
model, preprocess = llama.load("BIAS-7B", llama_dir, llama_type="7B", device=device)
model.eval()
prompt = llama.format_prompt("Please introduce this painting.")
img = Image.fromarray(cv2.imread("../docs/logo_v1.png"))
img = preprocess(img).unsqueeze(0).to(device)
result = model.generate(img, [prompt])[0]
print(result)
You need to request LLaMA's official weights. Our weights such as BIAS-7B
will be automatically downloaded.
您好,问题解决了吗 我也是同样的问题 找不到BIAS-7B的params.json 和 tokenizer.model文件