初始化项目，由ModelHub XC社区提供模型

Model: VietAI/gpt-j-6B-vietnamese-news
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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,39 @@
+---
+language: 
+  - vi
+tags:
+- pytorch
+- causal-lm
+- text-generation
+---
+
+# GPT-J 6B on Vietnamese News
+
+Details will be available soon.
+
+For more information, please contact anhduongng.1001@gmail.com (Dương) / imthanhlv@gmail.com (Thành) / nguyenvulebinh@gmail.com (Bình).
+
+### How to use
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("VietAI/gpt-j-6B-vietnamese-news")
+model = AutoModelForCausalLM.from_pretrained("VietAI/gpt-j-6B-vietnamese-news", low_cpu_mem_usage=True)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 
+model.to(device)
+
+prompt = "Tiềm năng của trí tuệ nhân tạo" # your input sentence
+input_ids = tokenizer(prompt, return_tensors="pt")['input_ids'].to(device)
+
+gen_tokens = model.generate(
+        input_ids,
+        max_length=max_length,
+        do_sample=True,
+        temperature=0.9,
+        top_k=20,
+    )
+
+gen_text = tokenizer.batch_decode(gen_tokens)[0]
+print(gen_text)
+```

config.json

@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "rotary": true,
+  "rotary_dim": 64,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.10.0.dev0",
+  "tokenizer_class": "GPT2Tokenizer",
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "temperature": 0.9,
+      "max_length": 150
+    }
+  },
+  "torch_dtype": "float16",
+  "use_cache": true,
+  "vocab_size": 60000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee1a7e020b045f68345db0916870b48a3cd5ebeff61c935ba32160c46a2b91e
+size 12263363254