feat: init

.gitattributes

@@ -6,12 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,39 @@
+---
+language: zh
+widget: 
+- text: "谁用谁知道？"
+license: apache-2.0
+---
+
+# liam168/chat-DialoGPT-small-zh
+
+## Model description
+
+用中文聊天数据训练的模型；
+
+### How to use
+
+Now we are ready to try out how the model works as a chatting partner!
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+mode_name = 'liam168/chat-DialoGPT-small-zh'
+tokenizer = AutoTokenizer.from_pretrained(mode_name)
+model = AutoModelForCausalLM.from_pretrained(mode_name)
+
+# Let's chat for 5 lines
+for step in range(5):
+	# encode the new user input, add the eos_token and return a tensor in Pytorch
+	new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
+
+	# append the new user input tokens to the chat history
+	bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
+
+	# generated a response while limiting the total chat history to 1000 tokens, 
+	chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+
+	# pretty print last ouput tokens from bot
+	print("Answer: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e2be6d12f77bf925a89f2381c6c685f4739752289039d590622d37d48a153d
+size 351265583

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}