Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<eop>": 151334,
+  "<sop>": 151333,
+  "<|assistant|>": 151337,
+  "<|begin_of_image|>": 151339,
+  "<|begin_of_video|>": 151341,
+  "<|end_of_image|>": 151340,
+  "<|end_of_video|>": 151342,
+  "<|endoftext|>": 151329,
+  "<|observation|>": 151338,
+  "<|system|>": 151335,
+  "<|user|>": 151336,
+  "[MASK]": 151330,
+  "[gMASK]": 151331,
+  "[sMASK]": 151332
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "ChatGLMForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForSequenceClassification"
+  },
+  "bias_dropout_fusion": true,
+  "classifier_dropout": null,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1.5625e-07,
+  "model_type": "chatglm",
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_layers": 40,
+  "original_rope": true,
+  "pad_token_id": 151329,
+  "padded_vocab_size": 151552,
+  "post_layer_norm": true,
+  "rmsnorm": true,
+  "rope_ratio": 500,
+  "seq_length": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 151552
+}

configuration_chatglm.py

@@ -0,0 +1,58 @@
+from transformers import PretrainedConfig
+
+
+class ChatGLMConfig(PretrainedConfig):
+    model_type = "chatglm"
+
+    def __init__(
+            self,
+            num_layers=28,
+            padded_vocab_size=65024,
+            hidden_size=4096,
+            ffn_hidden_size=13696,
+            kv_channels=128,
+            num_attention_heads=32,
+            seq_length=2048,
+            hidden_dropout=0.0,
+            classifier_dropout=None,
+            attention_dropout=0.0,
+            layernorm_epsilon=1e-5,
+            rmsnorm=True,
+            apply_residual_connection_post_layernorm=False,
+            post_layer_norm=True,
+            add_bias_linear=False,
+            add_qkv_bias=False,
+            bias_dropout_fusion=True,
+            multi_query_attention=False,
+            multi_query_group_num=1,
+            rope_ratio=1,
+            apply_query_key_layer_scaling=True,
+            attention_softmax_in_fp32=True,
+            fp32_residual_connection=False,
+            **kwargs
+    ):
+        self.num_layers = num_layers
+        self.vocab_size = padded_vocab_size
+        self.padded_vocab_size = padded_vocab_size
+        self.hidden_size = hidden_size
+        self.ffn_hidden_size = ffn_hidden_size
+        self.kv_channels = kv_channels
+        self.num_attention_heads = num_attention_heads
+        self.seq_length = seq_length
+        self.hidden_dropout = hidden_dropout
+        self.classifier_dropout = classifier_dropout
+        self.attention_dropout = attention_dropout
+        self.layernorm_epsilon = layernorm_epsilon
+        self.rmsnorm = rmsnorm
+        self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
+        self.post_layer_norm = post_layer_norm
+        self.add_bias_linear = add_bias_linear
+        self.add_qkv_bias = add_qkv_bias
+        self.bias_dropout_fusion = bias_dropout_fusion
+        self.multi_query_attention = multi_query_attention
+        self.multi_query_group_num = multi_query_group_num
+        self.rope_ratio = rope_ratio
+        self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
+        self.attention_softmax_in_fp32 = attention_softmax_in_fp32
+        self.fp32_residual_connection = fp32_residual_connection
+        super().__init__(**kwargs)

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "max_length": 128000,
+  "pad_token_id": 151329,
+  "temperature": 0.8,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b9f44204eb86785a2f84cf547ae6cacc7233733faa408a7fbe6453b26b43d0
+size 4930577664

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5789d72de70d618f5a1156e91bdcf1560f3ed7e4d7165404ec433d7d74e241a9
+size 4970581792

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1338b11b9557a41a61335f79cc44bd2a54070184dcbb9977f21dc11c782733ba
+size 4962191152

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77f92e2958dcc9584bdefce1ce0cd4296d12a7d4d6cfe2227e985e327c12d74
+size 4895065656

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9cd233ec5f03e35380be6c9770b7b310704987af97564e332160205328aa8b
+size 4895065656

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af91c59b2feb0455cb419e636bbdc3446f96986bcf04b962ca73968ee8e8d29e
+size 4895065656

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb230c7a7b4fa55920993274ac8d3e2b6fd7b672a94163da032d07a415fec39
+size 4895065656

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0c815343495b462d8c514ca80311be9395ba2f29498eab39262416f47040db
+size 3156230656

model.safetensors.index.json

@@ -0,0 +1,291 @@
+{
+  "metadata": {
+    "total_size": 37599805568
+  },
+  "weight_map": {
+    "transformer.embedding.word_embeddings.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.final_layernorm.weight": "model-00008-of-00008.safetensors",
+    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "transformer.encoder.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "transformer.encoder.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "transformer.encoder.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
+    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "transformer.output_layer.weight": "model-00008-of-00008.safetensors",
+    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00008.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "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
+  }
+}

tokenization_chatglm.py

@@ -0,0 +1,224 @@
+import regex as re
+import base64
+import os
+import tiktoken
+from typing import List, Optional, Union, Dict
+from transformers import PreTrainedTokenizer
+from transformers.utils import PaddingStrategy
+from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
+
+
+class ChatGLM4Tokenizer(PreTrainedTokenizer):
+    vocab_files_names = {"vocab_file": "tokenizer.model"}
+    model_input_names = ["input_ids", "attention_mask", "position_ids"]
+
+    def __init__(
+            self,
+            vocab_file,
+            clean_up_tokenization_spaces=False,
+            **kwargs
+    ):
+        self.name = "GLM4Tokenizer"
+        self.vocab_file = vocab_file
+        pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+        self.pat_str = re.compile(pat_str)
+
+        mergeable_ranks = {}
+        with open(vocab_file) as f:
+            for line in f:
+                token, rank = line.strip().split()
+                rank = int(rank)
+                token = base64.b64decode(token)
+                mergeable_ranks[token] = rank
+
+        self.mergeable_ranks = mergeable_ranks
+
+        self.tokenizer = tiktoken.Encoding(
+            name="my_tokenizer",
+            pat_str=pat_str,
+            mergeable_ranks=mergeable_ranks,
+            special_tokens={}
+        )
+        self.decoder = {rank: token for token, rank in mergeable_ranks.items()}
+        self.n_words = len(self.decoder)
+
+        super().__init__(
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            **kwargs
+        )
+
+    @property
+    def vocab_size(self):
+        return self.n_words
+
+    def get_vocab(self):
+        """ Returns vocab as a dict """
+        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str, int]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, int):
+                t = chr(t)
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors="replace")
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type int, bytes or str")
+        if temp:
+            text += temp.decode("utf-8", errors="replace")
+        return text
+
+    def _tokenize(self, text, **kwargs):
+        tokens = []
+        ids = self.tokenizer.encode(text)
+        for t in ids:
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.mergeable_ranks[token]
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.decoder.get(index, "")
+
+    def save_vocabulary(self, save_directory, filename_prefix=None):
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+            filename_prefix (`str`, *optional*):
+                An optional prefix to add to the named of the saved files.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if os.path.isdir(save_directory):
+            vocab_file = os.path.join(
+                save_directory, self.vocab_files_names["vocab_file"]
+            )
+        else:
+            vocab_file = save_directory
+
+        with open(self.vocab_file, 'rb') as fin:
+            proto_str = fin.read()
+
+        with open(vocab_file, "wb") as writer:
+            writer.write(proto_str)
+
+        return (vocab_file,)
+
+    def get_prefix_tokens(self):
+        prefix_tokens = [self.convert_tokens_to_ids("[gMASK]"), self.convert_tokens_to_ids("<sop>")]
+        return prefix_tokens
+
+    def build_single_message(self, role, metadata, message, tokenize=True):
+        assert role in ["system", "user", "assistant", "observation"], role
+        if tokenize:
+            role_tokens = [self.convert_tokens_to_ids(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n",
+                                                                                              disallowed_special=())
+            message_tokens = self.tokenizer.encode(message, disallowed_special=())
+            tokens = role_tokens + message_tokens
+            return tokens
+        else:
+            return str(f"<|{role}|>{metadata}\n{message}")
+
+    def build_inputs_with_special_tokens(
+            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A BERT sequence has the following format:
+
+        - single sequence: `[CLS] X [SEP]`
+        - pair of sequences: `[CLS] A [SEP] B [SEP]`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+        prefix_tokens = self.get_prefix_tokens()
+        token_ids_0 = prefix_tokens + token_ids_0
+        if token_ids_1 is not None:
+            token_ids_0 = token_ids_0 + token_ids_1 + [self.convert_tokens_to_ids("<eos>")]
+        return token_ids_0
+
+    def _pad(
+            self,
+            encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
+            max_length: Optional[int] = None,
+            padding_side: str = "left",
+            padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
+            pad_to_multiple_of: Optional[int] = None,
+            return_attention_mask: Optional[bool] = None,
+    ) -> dict:
+        """
+        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
+
+        Args:
+            encoded_inputs:
+                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
+            max_length: maximum length of the returned list and optionally padding length (see below).
+                Will truncate by taking into account the special tokens.
+            padding_strategy: PaddingStrategy to use for padding.
+
+                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
+                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
+                - PaddingStrategy.DO_NOT_PAD: Do not pad
+                The tokenizer padding sides are defined in self.padding_side:
+
+                    - 'left': pads on the left of the sequences
+                    - 'right': pads on the right of the sequences
+            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
+                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
+                `>= 7.5` (Volta).
+            return_attention_mask:
+                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
+        """
+        # Load from model defaults
+
+        required_input = encoded_inputs[self.model_input_names[0]]
+        seq_length = len(required_input)
+
+        if padding_strategy == PaddingStrategy.LONGEST:
+            max_length = len(required_input)
+
+        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
+            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
+
+        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
+
+        # Initialize attention mask if not present.
+        if "attention_mask" not in encoded_inputs:
+            encoded_inputs["attention_mask"] = [1] * seq_length
+
+        if "position_ids" not in encoded_inputs:
+            encoded_inputs["position_ids"] = list(range(seq_length))
+
+        if needs_to_be_padded:
+            difference = max_length - len(required_input)
+
+            if "attention_mask" in encoded_inputs:
+                encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
+            if "position_ids" in encoded_inputs:
+                encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
+            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
+
+        return encoded_inputs

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
+size 2623634

tokenizer_config.json

@@ -0,0 +1,149 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLM4Tokenizer",
+      null
+    ]
+  },
+  "chat_template": "{{ '[gMASK]<sop>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|assistant|>' }}{% elif message['role'] == 'assistant' %}{{ '\n' + content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "ChatGLM4Tokenizer"
+}