初始化项目，由ModelHub XC社区提供模型

Model: jesseD/homer-bot
Source: Original Platform

.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet 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
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- conversational
+language:
+- en
+---
+
+# HomerBot: A conversational chatbot imitating Homer Simpson
+
+This model is a fine-tuned [DialoGPT](https://huggingface.co/microsoft/DialoGPT-medium) (medium version) on Simpsons [scripts](https://www.kaggle.com/datasets/pierremegret/dialogue-lines-of-the-simpsons).
+
+More specifically, we fine-tune DialoGPT-medium for 3 epochs on 10K **(character utterance, Homer's response)** pairs
+
+For more details, check out our git [repo](https://github.com/jesseDingley/HomerBot) containing all the code.  
+
+### How to use
+
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch 
+
+tokenizer = AutoTokenizer.from_pretrained("DingleyMaillotUrgell/homer-bot")
+model = AutoModelForCausalLM.from_pretrained("DingleyMaillotUrgell/homer-bot")
+
+# 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,  
+        no_repeat_ngram_size=3,
+        do_sample=True, 
+        top_k=100, 
+        top_p=0.7,
+        temperature = 0.8
+    )
+    
+    # print last outpput tokens from bot
+    print("Homer: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
+```
+ 

added_tokens.json

@@ -0,0 +1 @@
+{"<|pad|>": 50257}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50258
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed4b70236e6ffb8e5d0429134d4b28fa3a2f3d2e62ef11c149294845acc84c0
+size 1444497848

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32373b1c4d139e646011ceca819ccf7b52b564e1404740f79102acbb0b52c8ae
+size 1444586585

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|pad|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "return_special_tokens_mask": true, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}