Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "ZhinaoForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_zhinao.ZhinaoConfig",
+    "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM"
+  },
+  "flah-attn_version": "2.5.5",
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.01,
+  "intermediate_size": 13056,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "zhinao",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 158464
+}

configuration_zhinao.py

@@ -0,0 +1,119 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class ZhinaoConfig(PretrainedConfig):
+    r"""
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 158464):
+            Vocabulary size of the Zhinao model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`ZhinaoModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 13056):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 32):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 4096):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 28):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import ZhinaoModel, ZhinaoConfig
+
+    >>> # Initializing a Zhinao style configuration
+    >>> configuration = ZhinaoConfig()
+
+    >>> # Initializing a model from the Zhinao-7B style configuration
+    >>> model = Zhinao2Model(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "zhinao"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=158464,
+        hidden_size=4096,
+        intermediate_size=13056,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.01,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window if use_sliding_window else None
+        self.max_window_layers = max_window_layers
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 158326,
+  "do_sample": true,
+  "eos_token_id": [
+    158326,
+    158332,
+    158333
+  ],
+  "pad_token_id": 158326,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e0ea009f7cea302c8afe67666e93ecd1c09c51c72eb8b68b17eaf26620d43f
+size 4991500768

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53721c92a51c8282e6b600899012711ced0aa48ec47130126c6b6d9605b61cad
+size 4997868656

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7c4cc4a03889e94bc8d9eaea7e507ce7f19612c631d7ba5b2ea86338a91869
+size 4261734000

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98c2af3c2dd9e42618ef961dd3c0c041da2c0bb4af819e78e216626e4ca96fd
+size 1298137216

model.safetensors.index.json

@@ -0,0 +1,266 @@
+{
+  "metadata": {
+    "total_size": 15549210624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<pad>"
+}

tokenization_zhinao.py

@@ -0,0 +1,261 @@
+import os
+import torch
+import base64
+import tiktoken
+from typing import Collection, Optional, Dict, List, Set, Tuple, Union
+from transformers import PreTrainedTokenizer
+from transformers.utils import PaddingStrategy
+from transformers.tokenization_utils import PreTrainedTokenizer
+
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+
+
+class SPTokenizer:
+    def __init__(self, model_path):
+        self.vocab_file = model_path
+        self.pad_token = '<pad>'
+        self.unk_token = '<unk>'
+        self.mask_token = '<mask>'
+        self.eod_token = '<eod>'
+        self.eop_token = '<eop>'
+        self.im_start_token = '<|im_start|>'
+        self.im_end_token = '<|im_end|>'
+
+        ## special_tokens
+        self.SPECIAL_TOKENS = (
+            self.pad_token,
+            self.unk_token,
+            self.mask_token,
+            self.eod_token,
+            self.eop_token,
+            '[space2]', '[space3]', '[space4]', '[space8]',
+            self.im_start_token, self.im_end_token
+        )
+        self.bulid_tokenizer()
+        self.out = self.output_core_token()
+        
+        self.token2strs = {
+            "[space2]": "  ",
+            "[space3]": "   ",
+            "[space4]": "    ",
+            "[space8]": "        ",
+        }
+        self.str2tokens = {v: k for k, v in self.token2strs.items()}
+        self.sorted_strs = sorted(list(self.str2tokens.keys()),
+                                  key=lambda x: len(x), reverse=True)
+        
+        ## skip_special_tokens
+        self.decode_skip_special_tokens = [
+            self.pad_token,
+            self.unk_token,
+            self.mask_token,
+            self.eod_token,
+            self.eop_token,
+            self.im_start_token,
+            self.im_end_token]
+        self.decode_skip_special_tokens_ids = [self.convert_token_to_id(token) for token in self.decode_skip_special_tokens]
+
+    def _load_tiktoken_bpe(self, tiktoken_bpe_file: str):
+        with open(tiktoken_bpe_file, "rb") as f:
+            contents = f.read()
+        return {
+            base64.b64decode(token): int(rank)
+            for token, rank in (line.split() for line in contents.splitlines() if line)
+        }
+    
+    def bulid_tokenizer(self):
+        mergeable_ranks = self._load_tiktoken_bpe(self.vocab_file)
+        special_tokens = {
+            token: index
+            for index, token in enumerate(
+                self.SPECIAL_TOKENS, start=len(mergeable_ranks)
+            )
+        }
+        encode = tiktoken.Encoding(
+            "zhinao",
+            pat_str=PAT_STR,
+            mergeable_ranks=mergeable_ranks,
+            special_tokens=special_tokens
+        )
+        decoder = {v: k for k, v in mergeable_ranks.items()}
+        decoder.update({v: k for k, v in special_tokens.items()})
+        decoder_token2id = {v: k for k, v in decoder.items()}
+    
+        self.tokenizer = encode
+        self.decoder = decoder
+        self.decoder_token2id = decoder_token2id
+        self.num_tokens = len(mergeable_ranks) + len(self.SPECIAL_TOKENS)
+
+    def output_core_token(self):
+        """output special tokens"""
+        out = {}
+        for t in self.SPECIAL_TOKENS:
+            out[t] = self.convert_token_to_id(t)
+        return out
+
+    def tokenize(
+            self, 
+            text, 
+            allowed_special: Union[Set, str] = "all",
+            disallowed_special: Union[Collection, str] = ()):
+        tokens = []
+        text = self.convert(text)
+        for idx in self.tokenizer.encode(text, allowed_special=allowed_special, disallowed_special=disallowed_special):
+            tokens.append(self.decoder[idx])
+        return tokens
+
+    def encode(self, text, allowed_special="all", disallowed_special=()):
+        """text to id"""
+        text = self.convert(text)
+        return self.tokenizer.encode(text, allowed_special=allowed_special, disallowed_special=disallowed_special)
+    
+    def decode(self, ids, errors="replace"):
+        """id to text"""
+        text = self.tokenizer.decode(ids, errors=errors)
+        return self.deconvert(text)
+
+    def decode_tokens(self, tokens: List[str]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors="ignore")
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type bytes or str")
+        if temp:
+            text += temp.decode("utf-8", errors="ignore")
+        return self.deconvert(text)
+
+    def convert_id_to_token(self, idx):
+        return self.decoder[idx]
+    
+    def convert_token_to_id(self, token):
+        return self.decoder_token2id[token]
+
+    def convert(self, text):
+        """将文本的特殊字符转换成特殊token"""
+        for k in ["[br]", "<br>"]:
+            text = text.replace(k, "\n")
+        for k in self.sorted_strs:
+            if k in text:
+                text = text.replace(k, self.str2tokens[k])
+        return text
+
+    def deconvert(self, text):
+        """将解码文本恢复原始字符"""
+        for t in self.token2strs:
+            if t in text:
+                text = text.replace(t, self.token2strs[t])
+        return text
+
+
+class ZhinaoTokenizer(PreTrainedTokenizer):
+    vocab_files_names = {"vocab_file": "vocab/360.tiktoken"}
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, **kwargs):
+        self.name = "ZhinaoTokenizer"
+        self.vocab_file = vocab_file
+        self.tokenizer = SPTokenizer(model_path=vocab_file)
+        try:
+            kwargs.pop('eos_token')
+            kwargs.pop('pad_token')
+            kwargs.pop('unk_token')
+        except:
+            pass
+        super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces, **kwargs)
+        self.pad_token_id = self.tokenizer.convert_token_to_id(self.tokenizer.pad_token)
+        self.eod_id = self.tokenizer.convert_token_to_id(self.tokenizer.eod_token)
+        self.im_start_id = self.tokenizer.convert_token_to_id(self.tokenizer.im_start_token)
+        self.im_end_id = self.tokenizer.convert_token_to_id(self.tokenizer.im_end_token)
+
+    @property
+    def eop_token(self) -> str:
+        return self.tokenizer.eop_token
+
+    @property
+    def eop_token_id(self):
+        return self.tokenizer.convert_token_to_id(self.tokenizer.eop_token)
+    
+    @property
+    def eos_token_id(self):
+        return self.tokenizer.convert_token_to_id(self.tokenizer.eod_token)
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.num_tokens
+
+    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 tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        split_special_tokens=False,
+    ) -> List[Union[bytes, str]]:
+        tokens = []
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.tokenizer.decoder[t])
+        return tokens
+    
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = "ignore",
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i not in self.tokenizer.decode_skip_special_tokens_ids]
+        return self.tokenizer.decode(token_ids, errors=errors)
+
+    def _tokenize(self, text, **kwargs):
+        raise NotImplementedError
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.tokenizer.convert_token_to_id(token)
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab. """
+        return self.tokenizer.convert_id_to_token(index)
+
+    def convert_tokens_to_string(self, tokens: List[str]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        return self.tokenizer.decode_tokens(tokens)
+
+    def save_vocabulary(self, save_directory, filename_prefix=None):
+        """Save only the vocabulary of the tokenizer (vocabulary). """
+        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()
+
+        os.makedirs(save_directory + "/vocab", exist_ok=True)
+        with open(vocab_file, "wb") as writer:
+            writer.write(proto_str)
+
+        return (vocab_file,)

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_zhinao.ZhinaoTokenizer",
+      null
+    ]
+  },
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ZhinaoTokenizer"
+}