diff --git a/config.json b/config.json new file mode 100644 index 0000000..78edecf --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "architectures": [ + "InternLM3ForCausalLM" + ], + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_internlm3.InternLM3Config", + "AutoModel": "modeling_internlm3.InternLM3Model", + "AutoModelForCausalLM": "modeling_internlm3.InternLM3ForCausalLM" + }, + "bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10240, + "max_position_embeddings": 32768, + "model_type": "internlm3", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 2, + "pad_token_id": 2, + "qkv_bias": false, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 6.0, + "rope_type": "dynamic" + }, + "rope_theta": 50000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.47.1", + "use_cache": true, + "vocab_size": 128512 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/configuration_internlm3.py b/configuration_internlm3.py new file mode 100644 index 0000000..d9f03ee --- /dev/null +++ b/configuration_internlm3.py @@ -0,0 +1,197 @@ +# coding=utf-8 +# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved. +# +# This code is based on transformers/src/transformers/models/llama/configuration_llama.py +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +""" InternLM3 model configuration""" + +from transformers.configuration_utils import PretrainedConfig +from transformers.modeling_rope_utils import rope_config_validation +from transformers.utils import logging + + +logger = logging.get_logger(__name__) + + +class InternLM3Config(PretrainedConfig): + r""" + This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate + an InternLM2 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 InternLM2-7B. + + 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 151936): + Vocabulary size of the InternLM3 model. Defines the number of different tokens that can be represented by the + `inputs_ids` passed when calling [`InternLM3Model`] + hidden_size (`int`, *optional*, defaults to 4096): + Dimension of the hidden representations. + intermediate_size (`int`, *optional*, defaults to 22016): + 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 32768): + 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. + rope_scaling (`Dict`, *optional*): + Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type + and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value + accordingly. + Expected contents: + `rope_type` (`str`): + The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', + 'llama3'], with 'default' being the original RoPE implementation. + `factor` (`float`, *optional*): + Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In + most scaling types, a `factor` of x will enable the model to handle sequences of length x * + original maximum pre-trained length. + `original_max_position_embeddings` (`int`, *optional*): + Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during + pretraining. + `attention_factor` (`float`, *optional*): + Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention + computation. If unspecified, it defaults to value recommended by the implementation, using the + `factor` field to infer the suggested value. + `beta_fast` (`float`, *optional*): + Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear + ramp function. If unspecified, it defaults to 32. + `beta_slow` (`float`, *optional*): + Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear + ramp function. If unspecified, it defaults to 1. + `short_factor` (`List[float]`, *optional*): + Only used with 'longrope'. The scaling factor to be applied to short contexts (< + `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden + size divided by the number of attention heads divided by 2 + `long_factor` (`List[float]`, *optional*): + Only used with 'longrope'. The scaling factor to be applied to long contexts (< + `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden + size divided by the number of attention heads divided by 2 + `low_freq_factor` (`float`, *optional*): + Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE + `high_freq_factor` (`float`, *optional*): + Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE + qkv_bias (`bool`, *optional*, defaults to `False`): + Whether to use a bias in the query, key and value projection layers during self-attention. + attention_dropout (`float`, *optional*, defaults to 0.0): + The dropout ratio for the attention probabilities. + bias (`bool`, *optional*, defaults to `False`): + Whether to use a bias in o_proj, up_proj, down_proj and gate_proj layers. + head_dim (`int`, *optional*): + The attention head dimension. If None, it will default to hidden_size // num_heads + + ```python + >>> from transformers import InternLM3Model, InternLM3Config + + >>> # Initializing a InternLM3 style configuration + >>> configuration = InternLM3Config() + + >>> # Initializing a model from the InternLM3-8B style configuration + >>> model = InternLM3Model(configuration) + + >>> # Accessing the model configuration + >>> configuration = model.config + ```""" + + model_type = "internlm3" + keys_to_ignore_at_inference = ["past_key_values"] + + # Default tensor parallel plan for base model `InternLM3` + 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", + } + + def __init__( + self, + vocab_size=128512, + hidden_size=4096, + intermediate_size=11008, + num_hidden_layers=32, + num_attention_heads=32, + num_key_value_heads=32, + hidden_act="silu", + max_position_embeddings=32768, + initializer_range=0.02, + rms_norm_eps=1e-6, + use_cache=True, + tie_word_embeddings=False, + rope_theta=10000.0, + rope_scaling=None, + qkv_bias=False, + attention_dropout=0.0, + 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 + + # 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.rope_scaling = rope_scaling + self.qkv_bias = qkv_bias + self.attention_dropout = attention_dropout + self.bias = bias + self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads + # Validate the correctness of rotary position embeddings parameters + # BC: if there is a 'type' field, move it to 'rope_type'. + 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__( + tie_word_embeddings=tie_word_embeddings, + **kwargs, + ) diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..cb6982c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 1, + "eos_token_id": [ + 2, + 128131 + ], + "pad_token_id": 2, + "transformers_version": "4.47.1" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..b9b1a7e --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a1b8c2aecbe72356241a5b5e861ba029f4e61189c4c0a9ca9821e66679f6f5 +size 9999626944 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..38a5d23 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eefc1671b07fe3aefb5011f381eb4524c27595cab06e56fbeac256ebe24b18d +size 9857121648