Create README.md

README.md

@@ -0,0 +1,52 @@
+---
+pipeline_tag: text-generation
+inference: true
+widget:
+- text: 'Hello!'
+  example_title: Hello world
+  group: Python
+library_name: transformers
+---
+
+This model is randomly initialized, using the config from [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b) but with smaller size. 
+Note:
+- The model uses "new architecture" in Falcon-40b.
+- The model is in float16.
+
+Codes:
+```python
+import transformers
+from optimum.intel.openvino import OVModelForCausalLM
+import torch
+import os
+from huggingface_hub import create_repo, upload_folder
+
+source_model_id = 'tiiuae/falcon-40b'
+save_path = '/tmp/yujiepan/falcon-new-tiny-random'
+repo_id = 'yujiepan/falcon-new-tiny-random'
+
+config = transformers.AutoConfig.from_pretrained(
+    source_model_id, trust_remote_code=True)
+config.hidden_size = 8
+config.num_attention_heads = 2
+config.num_hidden_layers = 2
+config.torch_dtype = torch.float16
+
+model = transformers.AutoModelForCausalLM.from_config(
+    config, trust_remote_code=True)
+model = model.half()
+model.save_pretrained(save_path)
+
+tokenizer = transformers.AutoTokenizer.from_pretrained(
+    source_model_id, trust_remote_code=True)
+tokenizer.save_pretrained(save_path)
+
+# current not supported, might add this later
+# ovmodel = OVModelForCausalLM.from_pretrained(
+#     save_path, export=True, trust_remote_code=True)
+# ovmodel.save_pretrained(save_path)
+
+os.system(f'ls -alh {save_path}')
+create_repo(repo_id, exist_ok=True)
+upload_folder(repo_id=repo_id, folder_path=save_path)
+```