Update README.md

README.md

@@ -10,7 +10,20 @@ tags:
 ---
 # TinyLlama-1.1B-32k
 
-#### NOTE: This is a fork of the original model at https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k but with fixed safetensors
+#### NOTE: This is a fork of the original model at https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k but with fixed safetensors metadata using the following code:
+
+```
+import safetensors
+from safetensors.torch import save_file
+
+tensors = dict()
+with safetensors.safe_open(safetensors_path, framework="pt") as f:
+    for key in f.keys():
+        tensors[key] = f.get_tensor(key)
+
+save_file(tensors, safetensors_path, metadata={'format': 'pt'})
+```
+(from https://huggingface.co/SeaLLMs/SeaLLM-7B-Hybrid/discussions/2#65752144412ee70185d49ff5)
 
 32k context finetune of TinyLlama-1.1B using increased rope theta (rope frequency base) meant to serve as a long-context speculative decoding model.