commit 00ad2d58a2e85dfba83b4fe9c2d824716fc4f98b Author: ModelHub XC Date: Wed Jun 3 05:56:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: nex-agi/internlm3-8B-Nex-N1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..948d360 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Nex-N1-TechReport.pdf b/Nex-N1-TechReport.pdf new file mode 100644 index 0000000..2586942 --- /dev/null +++ b/Nex-N1-TechReport.pdf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b32a420ccd3f74452e9932d04dc334b791c710f29c0d9d274745ea95572bedae +size 6464309 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2df5bf9 --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +license: apache-2.0 +--- + +
+ +
+ +--- + +
+🏠 Home Page   |    +🤗 Model   |    +🤗 Data   |    +📑 Tech Report   +
+ +# Nex-N1 + +Nex is a next-generation, full-stack agentic platform that brings foundation models, synthetic data pipelines, RL training, agent frameworks, and deployment tools together in one unified ecosystem. +DeepSeek-V3.1-Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. +We are committed to making it easier than ever to build and deploy AI agents by offering researchers and entrepreneurs a high-performance, reliable, and cost-effective "out-of-the-box" agent system. + +## Highlights + +- **Full spectrum model matrix:** From 8B to 671B parameters, the Nex series covers everything from edge-friendly setups to frontier-scale deployments. +- **Agent-focused performance:** Demonstrates industry-leading results on programming, tool-use, web-search, and other multi-hop reasoning tasks. +- **Production-ready utility:** Excels at mini-app development, website authoring, slide creation, and immersive role-play—delivering immediate productivity +gains. +- **End-to-end control:** Developers can build the entire data-to-deployment loop on top of Nex, ensuring sovereignty while keeping costs predictable. +- **Open ecosystem:** Turnkey synthetic data pipelines, curated datasets, Nex-N1 checkpoints, the NexAU Agent framework, the EaaS MoE inference stack, and NexRL +training services are all openly available. + +## Performance + +Nex-N1 is evaluated on six representative agentic benchmarks (general + professional). The model consistently ranks at or near the top across tool-using, web-search, and coding-heavy evaluations, showing strong readiness for real-world agent workflows. + +![Nex-N1 Benchmark Overview](./figures/Nex-N1-Benchamrk-white.png) + + + +Nex-N1 provides various size models from 8B to 671B for different usage scenarios. + +| Model | GAIA2 | τ2-Bench | SWE-bench Verified | Terminal-Bench2 | BaxBench | BFCL v4 | +| --- | --- | --- | --- | --- | --- | --- | +| [DeepSeek-V3.1-Nex-N1](https://huggingface.co/nex-agi/DeepSeek-V3.1-Nex-N1) | 29.5 | 80.2 | 70.6 | 31.8 | 59.7 | 65.3 | +| [Qwen3-32B-Nex-N1](https://huggingface.co/nex-agi/Qwen3-32B-Nex-N1) | 16.7 | 72.1 | 50.5 | 16.7 | 34.8 | 60.5 | +| [Qwen3-30B-A3B-Nex-N1](https://huggingface.co/nex-agi/Qwen3-30B-A3B-Nex-N1) | 11.3 | 65.3 | 29.7 | 8.3 | 13.6 | 51.9 | +| [internlm3-8B-Nex-N1](https://huggingface.co/nex-agi/internlm3-8B-Nex-N1) | 8.6 | 63.0 | 20.3 | - | - | 44.5 | + +Nex-N1 demonstrates competitive performance across all evaluation scenarios, showing particularly strong results in practical coding and HTML generation tasks. + +
+ +
Practical Coding Evaluation
+
+ +
+ +
HTML Generation Evaluation
+
+ +Refer to and for more details. + +## Usage + +### Local Deployment + +We recommend `sglang` for serving Nex-series models locally: + +```bash +python -m sglang.launch_server --model-path /path/to/your/model +``` + +### Function Calling + +Nex-series models support robust function-calling capabilities. To maximize the function-calling capabilities of the Nex-series models, we modified the tool parser of `qwen3_coder`, see: . To enable this feature, simply add the `--tool-call-parser qwen3_coder` flag when launching the server: + +```bash +python -m sglang.launch_server --model-path /path/to/your/model --tool-call-parser qwen3_coder +``` + +### Mini Program Development + +Nex-N1 is optimized for mini program development. For optimal performance, we recommend using Claude Code configured with both `context7` and a search MCP. + +```shell +claude mcp add --transport http context7 https://mcp.context7.com/mcp --header "CONTEXT7_API_KEY: [CONTEXT7_API_KEY]" + +claude mcp add --transport stdio serper-search --env SERPER_API_KEY=[SERPER_API_KEY] -- npx -y serper-search-scrape-mcp-server +``` + +Refer to for more details on setting up `context7`. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..f810da6 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,160 @@ +{% macro render_item_list(item_list, tag_name='required') %} + {%- if item_list is defined and item_list is iterable and item_list | length > 0 %} + {%- if tag_name %}{{- '\n<' ~ tag_name ~ '>' -}}{% endif %} + {{- '[' }} + {%- for item in item_list -%} + {%- if loop.index > 1 %}{{- ", "}}{% endif -%} + {%- if item is string -%} + {{ "`" ~ item ~ "`" }} + {%- else -%} + {{ item }} + {%- endif -%} + {%- endfor -%} + {{- ']' }} + {%- if tag_name %}{{- '' -}}{% endif %} + {%- endif %} +{% endmacro %} + +{%- if not add_generation_prompt is defined %} + {% set add_generation_prompt = false %} +{%- endif %} + +{%- set ns = namespace(is_first=false, system_prompt='You are Nex, a helpful assistant.', is_first_sp=true, is_last_user=false) %} +{%- for message in messages %} + {%- if message['role'] == 'system' %} + {%- if ns.is_first_sp %} + {% set ns.system_prompt = message['content'] %} + {% set ns.is_first_sp = false %} + {%- else %} + {% set ns.system_prompt = ns.system_prompt ~ '\n\n' ~ message['content'] %} + {%- endif %} + {%- endif %} +{%- endfor -%} + +{%- if tools is defined and tools is not none %} + {% set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n\n' + '\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n' + 'IMPORTANT:\n' + '- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n' + '- Required parameters MUST be specified\n' + '- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n\n' + 'You have access to the following functions:\n\n' + '') %} + {% for tool in tools %} + {%- if tool.function is defined %} + {%- set tool = tool.function %} + {%- endif %} + {% set tool_ns.text = tool_ns.text ~ '\n\n' ~ tool.name ~ '' %} + {% set tool_ns.text = tool_ns.text ~ '\n' ~ (tool.description | trim) ~ '' %} + {% set tool_ns.text = tool_ns.text ~ '\n' %} + {%- for param_name, param_fields in tool.parameters.properties|items %} + {% set tool_ns.text = tool_ns.text ~ '\n' %} + {% set tool_ns.text = tool_ns.text ~ '\n' ~ param_name ~ '' %} + {%- if param_fields.type is defined %} + {% set tool_ns.text = tool_ns.text ~ '\n' ~ (param_fields.type | string) ~ '' %} + {%- endif %} + {%- if param_fields.description is defined %} + {% set tool_ns.text = tool_ns.text ~ '\n' ~ (param_fields.description | trim) ~ '' %} + {%- endif %} + {%- if param_fields.enum is defined and param_fields.enum is iterable and param_fields.enum | length > 0 %} + {% set tool_ns.text = tool_ns.text ~ render_item_list(param_fields.enum, 'enum') %} + {%- endif %} + {%- set handled_keys = ['type', 'description', 'enum', 'required'] %} + {%- for json_key in param_fields.keys() | reject("in", handled_keys) %} + {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %} + {%- if param_fields[json_key] is mapping %} + {% set tool_ns.text = tool_ns.text ~ '\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | tojson | safe) ~ '' %} + {%- else %} + {% set tool_ns.text = tool_ns.text ~ '\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | string) ~ '' %} + {%- endif %} + {%- endfor %} + {%- if param_fields.required is defined and param_fields.required is iterable and param_fields.required | length > 0 %} + {% set tool_ns.text = tool_ns.text ~ render_item_list(param_fields.required, 'required') %} + {%- endif %} + {% set tool_ns.text = tool_ns.text ~ '\n' %} + {%- endfor %} + {%- if tool.parameters.required is defined and tool.parameters.required is iterable and tool.parameters.required | length > 0 %} + {% set tool_ns.text = tool_ns.text ~ render_item_list(tool.parameters.required, 'required') %} + {%- endif %} + {% set tool_ns.text = tool_ns.text ~ '\n' %} + {%- if tool.return is defined %} + {%- if tool.return is mapping %} + {% set tool_ns.text = tool_ns.text ~ '\n' ~ (tool.return | tojson | safe) ~ '' %} + {%- else %} + {% set tool_ns.text = tool_ns.text ~ '\n' ~ (tool.return | string) ~ '' %} + {%- endif %} + {%- endif %} + {% set tool_ns.text = tool_ns.text ~ '\n' %} + {% endfor %} + {% set tool_ns.text = tool_ns.text ~ '\n' %} + {% set ns.system_prompt = ns.system_prompt ~ '\n\n' ~ tool_ns.text %} +{%- endif %} + +{%- if ns.system_prompt %} + {{- '<|im_start|>system\n' ~ ns.system_prompt ~ '<|im_end|>\n' }} +{%- endif %} + +{%- for message in messages %} + {% set content = message['content'] %} + {%- if content is none %} + {% set content = '' %} + {%- endif %} + {%- if message['role'] == 'user' %} + {%- set ns.is_first = false -%} + {%- set ns.is_last_user = true -%} + {{- '<|im_start|>user\n' ~ content ~ '<|im_end|>\n' }} + {%- endif %} + {%- if message['role'] == 'assistant' %} + {% if '' in content %} + {% set content = content.split('')[-1] %} + {% endif %} + {% endif %} + {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %} + {%- set ns.is_last_user = false -%} + {%- set ns.is_first = false %} + {{- '<|im_start|>assistant' }} + {%- if content is defined and content is not none and content | trim | length > 0 %} + {{- '\n' + content | trim + '\n' }} + {%- endif %} + {%- for tool in message['tool_calls'] %} + {%- if tool.function is defined %} + {%- set tool_call = tool.function %} + {%- else %} + {%- set tool_call = tool %} + {%- endif %} + {{- '\n\n\n' }} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value if args_value is string else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {{- '<|im_end|>\n'}} + {%- endif %} + {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%} + {%- set ns.is_last_user = false -%} + {{- '<|im_start|>assistant\n' ~ content ~ '<|im_end|>\n'}} + {%- endif %} + {%- if message['role'] == 'tool' %} + {%- set ns.is_last_user = false -%} + {%- if loop.previtem and loop.previtem['role'] != 'tool' %} + {{- '<|im_start|>user\n' }} + {%- endif %} + {{- '\n' }} + {{- content }} + {{- '\n\n' }} + {%- if not loop.last and loop.nextitem['role'] != 'tool' %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor -%} +{% if add_generation_prompt %} + {{- '<|im_start|>assistant\n'}} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..f6d76bc --- /dev/null +++ b/config.json @@ -0,0 +1,41 @@ +{ + "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, + 128131, + 128129 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10240, + "max_position_embeddings": 131072, + "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 +} 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/figures/NEX_logo.svg b/figures/NEX_logo.svg new file mode 100644 index 0000000..a6bb933 --- /dev/null +++ b/figures/NEX_logo.svg @@ -0,0 +1,7 @@ + + + + + + + diff --git a/figures/Nex-N1-Benchamrk-white.png b/figures/Nex-N1-Benchamrk-white.png new file mode 100644 index 0000000..91076f4 Binary files /dev/null and b/figures/Nex-N1-Benchamrk-white.png differ diff --git a/figures/coding-eval.png b/figures/coding-eval.png new file mode 100644 index 0000000..5a8c4ef --- /dev/null +++ b/figures/coding-eval.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ee86e410634ca6b74e3972ce8d5ca27921af3f8b54afba2b5532b51fc17f07 +size 282848 diff --git a/figures/html-eval.png b/figures/html-eval.png new file mode 100644 index 0000000..6b0a0ec --- /dev/null +++ b/figures/html-eval.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f32196b03b76469f6ab0c000267b2993dd1f2c921c949482845ddd62a995547 +size 284325 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d5d8504 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "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..b13d6ff --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e28ee05a0b63d7913996bc1d219b13385fa20813cfa92b5fead99bbcf74535d +size 4999820088 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..6df90a5 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0be81604dcef205a264dc3721c7016fca7c9ffcee306a10d1795fff0598df46 +size 4928568784 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..e14e101 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50407dba2bf0a72ac0ea640fe634ebe6e2c33c2727c1ba8398ad12f9c1641341 +size 4928568784 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..965fdd9 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd243f94aae95bb1871f1ae4ecf2d01eaf2e41c385fc8bcd22c4e22e87d35748 +size 2751575736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..f76d404 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,442 @@ +{ + "metadata": { + "total_size": 17608482816 + }, + "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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-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-00002-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.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-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.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_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.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_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.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_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.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00004-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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_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.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a3df95b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,54 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|action_start|>", + "<|action_end|>", + "<|interpreter|>", + "<|plugin|>", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenization_internlm3.py b/tokenization_internlm3.py new file mode 100644 index 0000000..f68147f --- /dev/null +++ b/tokenization_internlm3.py @@ -0,0 +1,294 @@ +import os +from shutil import copyfile +from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple + +import sentencepiece as spm +from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer +from transformers.utils import logging + +if TYPE_CHECKING: + from transformers.tokenization_utils_base import TextInput + +logger = logging.get_logger(__name__) + +VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} + +SPIECE_UNDERLINE = "▁" + + +class InternLM3Tokenizer(PreTrainedTokenizer): + """ + Construct a InternLM3 tokenizer. Based on byte-level Byte-Pair-Encoding. The default padding token is unset as there is + no padding token in the original model. + + Args: + vocab_file (`str`): + Path to the vocabulary file. + unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): + The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this + token instead. + bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): + The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token. + eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`): + The end of sequence token. + pad_token (`str` or `tokenizers.AddedToken`, *optional*): + A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by + attention mechanisms or loss computation. + sp_model_kwargs (`Dict[str, Any]`, `Optional`, *optional*): + Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for + SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things, + to set: + + - `enable_sampling`: Enable subword regularization. + - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout. + + - `nbest_size = {0,1}`: No sampling is performed. + - `nbest_size > 1`: samples from the nbest_size results. + - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) + using forward-filtering-and-backward-sampling algorithm. + + - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for + BPE-dropout. + + add_bos_token (`bool`, *optional*, defaults to `True`): + Whether or not to add an `bos_token` at the start of sequences. + add_eos_token (`bool`, *optional*, defaults to `False`): + Whether or not to add an `eos_token` at the end of sequences. + clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): + Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like + extra spaces. + use_default_system_prompt (`bool`, *optional*, defaults to `False`): + Whether or not the default system prompt for InternLM3 should be used. + spaces_between_special_tokens (`bool`, *optional*, defaults to `False`): + Whether or not to add spaces between special tokens. + spaces_for_interleaved_special_tokens (`bool`, *optional*, defaults to `False`): + Whether or not to add spaces between special tokens that are interleaved with normal tokens. + add_prefix_space (`bool`, *optional*, defaults to `True`): + Whether or not to add an initial space to the input. This allows to treat the leading word just as any + other word. Again, this should be set with `from_slow=True` to make sure it's taken into account. + """ + + vocab_files_names = VOCAB_FILES_NAMES + model_input_names = ["input_ids", "attention_mask"] + + def __init__( + self, + vocab_file, + unk_token="", + bos_token="", + eos_token="", + pad_token=None, + sp_model_kwargs: Optional[Dict[str, Any]] = None, + add_bos_token=True, + add_eos_token=False, + clean_up_tokenization_spaces=False, + use_default_system_prompt=False, + spaces_between_special_tokens=False, + spaces_for_interleaved_special_tokens=False, + add_prefix_space=True, + **kwargs, + ): + self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs + bos_token = AddedToken(bos_token, normalized=False, special=True) if isinstance(bos_token, str) else bos_token + eos_token = AddedToken(eos_token, normalized=False, special=True) if isinstance(eos_token, str) else eos_token + unk_token = AddedToken(unk_token, normalized=False, special=True) if isinstance(unk_token, str) else unk_token + pad_token = AddedToken(pad_token, normalized=False, special=True) if isinstance(pad_token, str) else pad_token + + self.vocab_file = vocab_file + self.add_bos_token = add_bos_token + self.add_eos_token = add_eos_token + self.use_default_system_prompt = use_default_system_prompt + self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) + self.sp_model.Load(vocab_file) + self.add_prefix_space = add_prefix_space + self.spaces_for_interleaved_special_tokens = spaces_for_interleaved_special_tokens + + vocab_size = self.sp_model.get_piece_size() + self.decoder = {i: self.sp_model.id_to_piece(i) for i in range(vocab_size)} + + super().__init__( + bos_token=bos_token, + eos_token=eos_token, + unk_token=unk_token, + pad_token=pad_token, + add_bos_token=add_bos_token, + add_eos_token=add_eos_token, + sp_model_kwargs=sp_model_kwargs, + clean_up_tokenization_spaces=clean_up_tokenization_spaces, + use_default_system_prompt=use_default_system_prompt, + spaces_between_special_tokens=spaces_between_special_tokens, + add_prefix_space=add_prefix_space, + **kwargs, + ) + + def __getstate__(self): + state = self.__dict__.copy() + state["sp_model"] = None + state["sp_model_proto"] = self.sp_model.serialized_model_proto() + return state + + def __setstate__(self, d): + self.__dict__.update(d) + self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) + self.sp_model.LoadFromSerializedProto(self.sp_model_proto) + + @property + def vocab_size(self): + """Returns vocab size""" + return self.sp_model.get_piece_size() + + def get_vocab(self): + """Returns vocab as a dict""" + vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)} + vocab.update(self.added_tokens_encoder) + return vocab + + def tokenize(self, text: "TextInput", **kwargs) -> List[str]: + """ + Args: + text: TextInput + Simply calls PreTrainedTokenizer's method + """ + return super().tokenize(text, **kwargs) + + def _tokenize(self, text, **kwargs): + """ + Args: + text: TextInput + Returns a tokenized string. The Gemma tokenizer never adds a prefix space. + """ + return self.sp_model.encode(text, out_type=str) + + def _convert_token_to_id(self, token): + """Converts a token (str) in an id using the vocab.""" + return self.sp_model.piece_to_id(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 convert_tokens_to_string(self, tokens): + """Converts a sequence of tokens (string) in a single string.""" + # since we manually add the prefix space, we have to remove it when decoding + if tokens[0].startswith(SPIECE_UNDERLINE) and self.add_prefix_space: + tokens[0] = tokens[0][1:] + + current_sub_tokens = [] + out_string = "" + prev_is_special = False + for i, token in enumerate(tokens): + # make sure that special tokens are not decoded using sentencepiece model + if token in self.all_special_tokens: + if not prev_is_special and i != 0 and self.spaces_for_interleaved_special_tokens: + out_string += " " + out_string += self.sp_model.decode(current_sub_tokens) + token + prev_is_special = True + current_sub_tokens = [] + else: + if ( + prev_is_special + and i == 1 + and self.add_prefix_space + and not token.startswith(SPIECE_UNDERLINE) + and self.spaces_for_interleaved_special_tokens + ): + out_string += " " + current_sub_tokens.append(token) + prev_is_special = False + out_string += self.sp_model.decode(current_sub_tokens) + return out_string + + def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]: + """ + Save the vocabulary and special tokens file to a directory. + + Args: + save_directory (`str`): + The directory in which to save the vocabulary. + + Returns: + `Tuple(str)`: Paths to the files saved. + """ + if not os.path.isdir(save_directory): + logger.error(f"Vocabulary path ({save_directory}) should be a directory") + return + out_vocab_file = os.path.join(save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]) + + if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file): + copyfile(self.vocab_file, out_vocab_file) + elif not os.path.isfile(self.vocab_file): + with open(out_vocab_file, "wb") as fi: + content_spiece_model = self.sp_model.serialized_model_proto() + fi.write(content_spiece_model) + + return (out_vocab_file,) + + def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None): + bos_token_id = [self.bos_token_id] if self.add_bos_token else [] + eos_token_id = [self.eos_token_id] if self.add_eos_token else [] + + output = bos_token_id + token_ids_0 + eos_token_id + + if token_ids_1 is not None: + output = output + bos_token_id + token_ids_1 + eos_token_id + + return output + + def get_special_tokens_mask( + self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False + ) -> List[int]: + """ + Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding + special tokens using the tokenizer `prepare_for_model` method. + + Args: + token_ids_0 (`List[int]`): + List of IDs. + token_ids_1 (`List[int]`, *optional*): + Optional second list of IDs for sequence pairs. + already_has_special_tokens (`bool`, *optional*, defaults to `False`): + Whether or not the token list is already formatted with special tokens for the model. + + Returns: + `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. + """ + if already_has_special_tokens: + return super().get_special_tokens_mask(token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True) + + bos_token_id = [1] if self.add_bos_token else [] + eos_token_id = [1] if self.add_eos_token else [] + + if token_ids_1 is None: + return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + bos_token_id + ([0] * len(token_ids_1)) + eos_token_id + + def create_token_type_ids_from_sequences(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]: + """ + Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT + sequence pair mask has the following format: + + ``` + 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 + | first sequence | second sequence | + ``` + + if token_ids_1 is None, only returns the first portion of the mask (0s). + + Args: + token_ids_0 (`List[int]`): + List of ids. + token_ids_1 (`List[int]`, *optional*): + Optional second list of IDs for sequence pairs. + + Returns: + `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s). + """ + bos_token_id = [self.bos_token_id] if self.add_bos_token else [] + eos_token_id = [self.eos_token_id] if self.add_eos_token else [] + + output = [0] * len(bos_token_id + token_ids_0 + eos_token_id) + + if token_ids_1 is not None: + output += [1] * len(bos_token_id + token_ids_1 + eos_token_id) + + return output diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..a4e70cb --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcacff3229854f5103ee7a85473a30ca9a8b3a68f3aae9b7479574b23ac2256b +size 2475075 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..11f7e9c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,248 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|plugin|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|interpreter|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|action_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|action_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|action_start|>", + "<|action_end|>", + "<|interpreter|>", + "<|plugin|>", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "auto_map": { + "AutoTokenizer": [ + "tokenization_internlm3.InternLM3Tokenizer", + null + ] + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": {}, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "InternLM3Tokenizer", + "unk_token": "", + "use_default_system_prompt": false +}