init

README.md

@@ -0,0 +1,26 @@
+# LLaMA based chinese keyword generator
+
+基於高品質中文資料訓練的中文關鍵字產生器。
+
+Base Model: [p208p2002/llama-traditional-chinese-120M](https://huggingface.co/p208p2002/llama-traditional-chinese-120M)
+
+## 使用方式
+### 範例
+#### 輸入
+```
+國內車市旺，10月單月掛 牌量衝上4萬台佳績，為40,540台，月增9%、年增11%；累計前十個月掛牌量逾39萬台，改寫近18年來新高紀錄，這樣的熱度將旺到年底。</s>
+```
+#### 輸出
+```
+汽車行業、車市、熱度</s>
+```
+
+### OpenLLM
+支援[OpenLLM](https://github.com/bentoml/OpenLLM)部屬使用。
+
+```bash
+$ openllm start opt --model-id p208p2002/llama-keyword-generator-zh2zh-120M
+```
+```bash
+$ openllm query CONTEXT</s>
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "p208p2002/llama-traditional-chinese-120M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712abda3e994824c19cac7b8bf8cb32a2976c883a2541096360f30320950e0b9
+size 479836230

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d35dc049e074a4d28a9e91c00fdb5f81b0438b11c7d39b8e0290d81937a3d1
+size 729777

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}