初始化项目，由ModelHub XC社区提供模型

Model: vlsp-2023-vllm/hoa-1b4
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 +1,66 @@
+---
+license: bigscience-bloom-rail-1.0
+language:
+- vi
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- bloom
+- causal-lm
+- pytorch
+model-index:
+- name: vlsp-2023-vllm/hoa-1b4
+  results:
+  - task:
+      name: Word prediction
+      type: text-generation
+    dataset:
+      type: vlsp-2023-vllm/vi_lambada
+      name: vi_lambada
+      split: test
+    metrics:
+    - type: Perplexity
+      value: 8.606673731963474
+  - task:
+      name: Fewshot Translation
+      type: translation
+    dataset:
+      type: vlsp-2023-vllm/en-to-vi-formal-informal-tranlations
+      name: English to Vietnamese Formal/Informal translation
+      split: test
+    metrics:
+    - type: SacreBLEU
+      value: 25.5
+datasets:
+- vlsp-2023-vllm/vi_lambada
+metrics:
+- perplexity
+---
+
+# Hoa 1B4 (Bloom architecture)
+
+Hoa is an autoregressive Large Language Model (LLM), based on Bloom's model architecture. 
+Hoa was trained on part of the Common Crawl dataset in Vietnamese and English.
+
+Details will be available soon.
+
+To contact us, mail to: leanhcuong@gmail.com (Lê Anh Cường) | hieunguyen1053@outlook.com (Hiếu) | nv.cuong@int2.vn (Nguyễn Việt Cường)
+
+### How to use 
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("vlsp-2023-vllm/hoa-1b4")
+model = AutoModelForCausalLM.from_pretrained("vlsp-2023-vllm/hoa-1b4", low_cpu_mem_usage=True)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 
+model.to(device)
+
+prompt = "Địa chỉ trường Đại học Tôn Đức Thắng nằm ở số"
+input_ids = tokenizer(prompt, return_tensors="pt")['input_ids'].to(device)
+
+gen_tokens = model.generate(input_ids, max_length=max_length, repetition_penalty=1.1)
+
+print(tokenizer.batch_decode(gen_tokens)[0])
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "checkpoints1/checkpoint-11210",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 2,
+  "seq_length": 4096,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "unk_token_id": 0,
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.28.1",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170cf7305375e831b37ed6eb91a3e96f860ea0c42cbc6ffedc2c79112b2058d4
+size 5246166560

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a716e1cad447859eb432ae6269897a6913f813315ab039888f7866c1c80b62b3
+size 5246227937

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<|endoftext|>"
+}