初始化项目，由ModelHub XC社区提供模型

Model: VLAI-AIVN/vigpt2-aio
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 +1,100 @@
+---
+language:
+- vi
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- gpt2
+- vietnamese
+- text-generation
+- causal-lm
+model_type: gpt2
+datasets:
+- bkai-foundation-models/BKAINewsCorpus
+---
+
+# ViGPT2 AIO
+
+ViGPT2 AIO is a Vietnamese GPT-2 style causal language model pretrained for open-ended text generation and general Vietnamese language modeling.
+
+This model was developed to support teaching and hands-on practice in the [AIO](https://aivietnam.edu.vn/) course, while also serving as a general Vietnamese pretrained language model for experimentation and downstream adaptation.
+
+## Model Details
+
+- **Model name:** ViGPT2 AIO
+- **Architecture:** GPT-2
+- **Task:** Causal language modeling / text generation
+- **Language:** Vietnamese
+- **Library:** Transformers
+- **Weights format:** Safetensors
+
+## Training Data
+
+The model was pretrained on a mixture of Vietnamese news and Vietnamese Wikipedia text.
+
+### Data Sources
+
+- **BKAINewsCorpus** from `bkai-foundation-models/BKAINewsCorpus`
+- **Vietnamese Wikipedia** collected through a custom crawling pipeline, then cleaned from raw wikitext into plain text
+
+### Data Processing
+
+Before pretraining, the corpora were cleaned and deduplicated.
+
+- The tokenizer was trained on the raw corpora:
+  - `bkai_train.parquet`
+  - `vi_wiki_articles_clean.parquet`
+- The language model was pretrained on deduplicated versions of these corpora.
+- In the final training mixture, the Vietnamese Wikipedia corpus was upweighted relative to the news corpus.
+
+### Training Mixture
+
+The pretraining mixture used:
+
+- `bkai_train.parquet` with weight **1**
+- `vi_wiki_articles_clean.parquet` with weight **3**
+
+## Training Objective
+
+The model was pretrained with a standard causal language modeling objective, where the model learns to predict the next token in a sequence.
+
+## Limitations
+
+- The model may generate incorrect, nonsensical, or fabricated content.
+- Outputs can reflect biases or artifacts present in the pretraining data.
+- The model is not a verified factual source and should not be used without human validation in high-stakes settings.
+
+## Usage
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+repo_id = "VLAI-AIVN/vigpt2-aio"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+
+model = AutoModelForCausalLM.from_pretrained(repo_id)
+model.config.pad_token_id = tokenizer.pad_token_id
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device).eval()
+
+prompt = "Việt Nam là một đất nước"
+inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=80,
+        do_sample=True,
+        temperature=0.8,
+        top_p=0.9,
+        repetition_penalty=1.1,
+        pad_token_id=tokenizer.pad_token_id,
+    )
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_implementation": "flash_attention_2",
+  "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_inner": null,
+  "n_layer": 12,
+  "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": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.4",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc09b47ed3cc59b30c75e97a603386f3042b4eb109d12fb2173600be240ee87c
+size 497774208

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa302f1b8fc516997ab0158c95e276636e189bdf0241f32a3964a46e8ad142e
+size 5777