| |
| |
| |
| |
| |
| |
|
|
| from ...configuration_utils import PretrainedConfig |
| from ...modeling_rope_utils import rope_config_validation |
|
|
|
|
| class MyNewModel2Config(PretrainedConfig): |
| r""" |
| This is the configuration class to store the configuration of a [`GemmaModel`]. It is used to instantiate an Gemma |
| model according to the specified arguments, defining the model architecture. Instantiating a configuration with the |
| defaults will yield a similar configuration to that of the Gemma-7B. |
| e.g. [google/gemma-7b](https://huggingface.co/google/gemma-7b) |
| 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 256000): |
| Vocabulary size of the Gemma model. Defines the number of different tokens that can be represented by the |
| `inputs_ids` passed when calling [`GemmaModel`] |
| ```python |
| >>> from transformers import GemmaModel, GemmaConfig |
| >>> # Initializing a Gemma gemma-7b style configuration |
| >>> configuration = GemmaConfig() |
| >>> # Initializing a model from the gemma-7b style configuration |
| >>> model = GemmaModel(configuration) |
| >>> # Accessing the model configuration |
| >>> configuration = model.config |
| ```""" |
|
|
| model_type = "my_new_model2" |
| keys_to_ignore_at_inference = ["past_key_values"] |
| |
| base_model_tp_plan = { |
| "layers.*.self_attn.q_proj": "colwise", |
| "layers.*.self_attn.k_proj": "colwise", |
| "layers.*.self_attn.v_proj": "colwise", |
| "layers.*.self_attn.o_proj": "rowwise", |
| "layers.*.mlp.gate_proj": "colwise", |
| "layers.*.mlp.up_proj": "colwise", |
| "layers.*.mlp.down_proj": "rowwise", |
| } |
| base_model_pp_plan = { |
| "embed_tokens": (["input_ids"], ["inputs_embeds"]), |
| "layers": (["hidden_states", "attention_mask"], ["hidden_states"]), |
| "norm": (["hidden_states"], ["hidden_states"]), |
| } |
|
|
| def __init__( |
| self, |
| vocab_size=32000, |
| hidden_size=4096, |
| intermediate_size=11008, |
| num_hidden_layers=32, |
| num_attention_heads=32, |
| num_key_value_heads=None, |
| hidden_act="silu", |
| max_position_embeddings=2048, |
| initializer_range=0.02, |
| rms_norm_eps=1e-6, |
| use_cache=True, |
| pad_token_id=None, |
| bos_token_id=1, |
| eos_token_id=2, |
| pretraining_tp=1, |
| tie_word_embeddings=False, |
| rope_theta=10000.0, |
| rope_scaling=None, |
| attention_bias=False, |
| attention_dropout=0.0, |
| mlp_bias=False, |
| head_dim=None, |
| **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 |
|
|
| |
| 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.pretraining_tp = pretraining_tp |
| self.use_cache = use_cache |
| self.rope_theta = rope_theta |
| self.rope_scaling = rope_scaling |
| self.attention_bias = attention_bias |
| self.attention_dropout = attention_dropout |
| self.mlp_bias = mlp_bias |
| self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads |
| |
| |
| if self.rope_scaling is not None and "type" in self.rope_scaling: |
| self.rope_scaling["rope_type"] = self.rope_scaling["type"] |
| rope_config_validation(self) |
|
|
| super().__init__( |
| pad_token_id=pad_token_id, |
| bos_token_id=bos_token_id, |
| eos_token_id=eos_token_id, |
| tie_word_embeddings=tie_word_embeddings, |
| **kwargs, |
| ) |
|
|
