Upload 10 files

ChatLM-mini-Chinese/.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

ChatLM-mini-Chinese/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./model_save/dpo/",
+  "architectures": [
+    "TextToTextModel"
+  ],
+  "auto_map": {
+    "AutoModelForSeq2SeqLM": "modeling_chat_model.TextToTextModel"
+  },
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 10,
+  "num_heads": 12,
+  "num_layers": 10,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 29298
+}

ChatLM-mini-Chinese/configuration_chat_model.py

@@ -0,0 +1,4 @@
+from transformers import T5Config
+
+class TextToTextModelConfig(T5Config):
+    model_type = 't5'

ChatLM-mini-Chinese/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

ChatLM-mini-Chinese/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054caeae92bcc13f0b6e7a12f86e75c8e18117279ecd89c4aa1f8ac74c95c02a
+size 750794624

ChatLM-mini-Chinese/modeling_chat_model.py

@@ -0,0 +1,74 @@
+import torch
+from torch import Tensor, LongTensor
+from transformers import T5ForConditionalGeneration, T5Config
+from transformers import TextIteratorStreamer
+from transformers.generation.configuration_utils import GenerationConfig
+
+class TextToTextModel(T5ForConditionalGeneration):
+    def __init__(self, config: T5Config) -> None:
+        '''
+            TextToTextModel继承T5ForConditionalGeneration
+        '''
+        super().__init__(config)
+    
+    @torch.no_grad()
+    def my_generate(self, 
+                input_ids: LongTensor, 
+                attention_mask: LongTensor, 
+                max_seq_len: int=256,
+                search_type: str='beam',
+                streamer: TextIteratorStreamer=None,
+            ) -> Tensor:
+        '''
+        自定义gennerate方法方便调用、测试
+        search_type: ['greedy', 'beam', 'sampling', 'contrastive', ]
+
+        - *greedy decoding* by calling [`~generation.GenerationMixin.greedy_search`] if `num_beams=1` and
+            `do_sample=False`
+        - *contrastive search* by calling [`~generation.GenerationMixin.contrastive_search`] if `penalty_alpha>0.`
+            and `top_k>1`
+        - *multinomial sampling* by calling [`~generation.GenerationMixin.sample`] if `num_beams=1` and
+            `do_sample=True`
+        - *beam-search decoding* by calling [`~generation.GenerationMixin.beam_search`] if `num_beams>1` and
+            `do_sample=False`
+        - *beam-search multinomial sampling* by calling [`~generation.GenerationMixin.beam_sample`] if
+            `num_beams>1` and `do_sample=True`
+        '''
+        generation_config = GenerationConfig()
+        generation_config.remove_invalid_values = True
+        generation_config.eos_token_id = 1
+        generation_config.pad_token_id = 0
+        generation_config.decoder_start_token_id = self.config.decoder_start_token_id
+        generation_config.max_new_tokens = max_seq_len
+        # generation_config.repetition_penalty = 1.1 # 重复词惩罚
+
+        if search_type == 'greedy':
+            generation_config.num_beams = 1
+            generation_config.do_sample = False
+        elif search_type == 'beam':
+            generation_config.top_k = 50
+            generation_config.num_beams = 5
+            generation_config.do_sample = True
+            generation_config.top_p = 0.95
+            generation_config.no_repeat_ngram_size = 4
+            generation_config.length_penalty = -2.0
+            generation_config.early_stopping = True
+        elif search_type == 'sampling':
+            generation_config.num_beams = 1
+            generation_config.do_sample = True
+            generation_config.top_k = 50
+            generation_config.temperature = 0.98   # 越低概率越趋向于均匀分布
+            generation_config.top_p = 0.80
+            generation_config.no_repeat_ngram_size = 4
+        elif search_type == 'contrastive':
+            generation_config.penalty_alpha = 0.5
+            generation_config.top_k = 50
+
+        result = self.generate(
+            inputs=input_ids,
+            attention_mask=attention_mask,
+            generation_config=generation_config,
+            streamer=streamer,
+            )
+
+        return result

ChatLM-mini-Chinese/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "[EOS]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

ChatLM-mini-Chinese/tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}