初始化项目，由ModelHub XC社区提供模型

Model: ShikoShin/GPT2-Medium-MORIAI
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,222 @@
+---
+library_name: transformers
+license: apache-2.0
+language:
+- en
+base_model:
+- openai-community/gpt2-medium
+---
+
+# MORI AI
+
+## Model Details
+
+### Model Description
+
+MORI (Machine-Oriented Responsive Intelligence) is a transformer-based conversational AI developed as part of the research project:
+
+**"Design and Implementation of an NLP-Driven Intelligent Web Companion for Real-Time User Interaction."**
+
+This version of MORI is specifically designed to assist students, faculty, and stakeholders of ICCT Colleges – San Mateo Campus by providing information related to academic programs, enrollment procedures, registrar services, school policies, and general campus inquiries.
+
+The model focuses on answering institution-related questions and providing guidance based on publicly available academic and administrative information.
+
+**Developed by:** ShikoShin
+**Model Type:** Transformer-Based Conversational AI
+**Language(s):** English
+**License:** Apache 2.0
+**Finetuned from:** DialoGPT-Large
+
+---
+
+# Model Sources
+
+**Institution:** ICCT Colleges
+
+**Research Project:** Design and Implementation of an NLP-Driven Intelligent Web Companion for Real-Time User Interaction
+
+---
+
+# Intended Use
+
+## Primary Use Cases
+
+MORI is intended to assist users with:
+
+* Academic program inquiries
+* Course information
+* Admission requirements
+* Enrollment procedures
+* Registrar-related concerns
+* School policies and guidelines
+* Frequently asked questions about ICCT Colleges – San Mateo Campus
+
+## Educational Support
+
+The model may be integrated into:
+
+* Student assistance platforms
+* School websites
+* Mobile applications
+* Information kiosks
+* Academic support systems
+
+---
+
+# Out-of-Scope Use
+
+MORI is not intended for:
+
+* Medical advice
+* Legal advice
+* Financial consulting
+* Psychological counseling
+* Emergency response
+* Safety-critical decision making
+
+Users should consult official ICCT personnel for authoritative decisions regarding academic records, enrollment status, and institutional policies.
+
+---
+
+# Training Data
+
+## Dataset Description
+
+MORI was trained using a curated dataset consisting of institution-specific information related to:
+
+* Academic courses and programs
+* Enrollment workflows
+* Admission requirements
+* Registrar procedures
+* Frequently asked student inquiries
+* Publicly available institutional information
+
+### Data Privacy Statement
+
+No sensitive personal information was used during training.
+
+The dataset does **not** contain:
+
+* Student records
+* Grades or transcripts
+* Personal identification information
+* Financial records
+* Medical information
+* Confidential institutional documents
+
+Training data was limited to educational and administrative information intended for public dissemination.
+
+---
+
+# Limitations
+
+MORI may:
+
+* Generate incorrect responses
+* Provide outdated information if institutional policies change
+* Misinterpret ambiguous questions
+* Require human verification for official transactions
+
+The model should be treated as an informational assistant rather than an official source of record.
+
+---
+
+# How to Get Started
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_name = "ShikoShin/DialoGPT-Large-MORIAI"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+prompt = "How do I enroll at ICCT San Mateo?"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=100,
+    do_sample=True,
+    temperature=0.8
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+# Training Procedure
+
+## Preprocessing
+
+The dataset underwent:
+
+* Data cleaning
+* Duplicate removal
+* Text normalization
+* Formatting into question-answer pairs
+* Tokenization
+
+## Framework
+
+* Python
+* PyTorch
+* Hugging Face Transformers
+* Hugging Face Tokenizers
+
+---
+
+# Evaluation
+
+## Evaluation Criteria
+
+The model was evaluated based on:
+
+* Response relevance
+* Institutional information accuracy
+* Conversational consistency
+* User query understanding
+
+## Results
+
+MORI demonstrated the ability to answer common student and administrative questions related to ICCT Colleges – San Mateo Campus while maintaining conversational coherence.
+
+---
+
+# Technical Specifications
+
+## Architecture
+
+Transformer-based autoregressive language model fine-tuned from DialoGPT-Large.
+
+### Objective
+
+Generate contextually appropriate responses to institution-related inquiries while maintaining conversational flow.
+
+---
+
+# Citation
+
+### APA
+
+ShikoShin. (2026). MORI: Intelligent Academic Assistant for ICCT Colleges – San Mateo Campus. Hugging Face.
+
+### BibTeX
+
+@misc{mori2026,
+author = {ShikoShin},
+title = {MORI: Intelligent Academic Assistant for ICCT Colleges -- San Mateo Campus},
+year = {2026},
+publisher = {Hugging Face}
+}
+
+---
+
+# Authors
+
+ShikoShin
+
+---
+
+# Contact
+
+For questions, feedback, or collaboration opportunities, please contact the repository owner through Hugging Face.

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}

config.json

@@ -0,0 +1,43 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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,
+  "n_special": 0,
+  "pad_token_id": 50256,
+  "predict_special_tokens": true,
+  "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": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 50259
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed4e77e976eda0f467b6eda80379cfa55e810c007e9a617ae3c2c815db37bfd
+size 1419331072

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<user>",
+    "<mori>"
+  ],
+  "is_local": true,
+  "max_length": 128,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}