Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+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 [THUDM/chatglm3-6b-128k](https://huggingface.co/THUDM/chatglm3-6b-128k/blob/main/config.json) but with smaller size. 
+Note the model is in float16.
+
+Codes:
+```python
+import transformers
+import torch
+import os
+from huggingface_hub import create_repo, upload_folder
+
+source_model_id = 'THUDM/chatglm3-6b-128k'
+tiny_random_name = 'chatglm3-tiny-random'
+save_path = f'/tmp/yujiepan/{tiny_random_name}'
+repo_id = f'yujiepan/{tiny_random_name}'
+
+config = transformers.AutoConfig.from_pretrained(
+    source_model_id, trust_remote_code=True)
+config.hidden_size = 4
+config.ffn_hidden_size = 6
+config.num_attention_heads = 4
+config.kv_channels = 2
+config.num_layers = 2
+config.torch_dtype = torch.float16
+
+model = transformers.AutoModelForCausalLM.from_config(
+    config, trust_remote_code=True, torch_dtype=torch.float16)
+model = model.half()
+
+tokenizer = transformers.AutoTokenizer.from_pretrained(
+    source_model_id, trust_remote_code=True)
+
+# result = transformers.pipelines.pipeline(
+#     'text-generation',
+#     model=model, tokenizer=tokenizer,
+#     device=0,
+#     max_new_tokens=16,
+# )('Hello')
+# print(result)
+model = model.cuda()
+response, history = model.chat(tokenizer, "Hi", history=[], max_length=32)
+print(response)
+
+model.save_pretrained(save_path)
+tokenizer.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)
+```