初始化项目，由ModelHub XC社区提供模型
Model: sokada/codegen25-7b-multi-gguf-with-dummy-tokenizer Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt 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
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz 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
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl 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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* 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
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
136
README.md
Normal file
136
README.md
Normal file
@@ -0,0 +1,136 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- bigcode/starcoderdata
|
||||
language:
|
||||
- code
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# This repo is a fork for flatline_lsp
|
||||
|
||||
See [flatline_lsp](https://github.com/okdshin/flatline_lsp).
|
||||
|
||||
This repository is a fork of [Salesforce/codegen25-7b-multi](https://huggingface.co/Salesforce/codegen25-7b-multi).
|
||||
This repository contains gguf files but its tokenizer is dummy.
|
||||
|
||||
---
|
||||
|
||||
# CodeGen2.5-7B-multi
|
||||
|
||||
Title: [**CodeGen2.5: Small, but mighty**](https://blog.salesforceairesearch.com/codegen25)
|
||||
|
||||
Authors: [Erik Nijkamp](https://eriknijkamp.com)\*, [Hiroaki Hayashi](https://hiroakih.me)\*, Yingbo Zhou, Caiming Xiong
|
||||
|
||||
(\* equal contribution)
|
||||
|
||||
## Model description
|
||||
|
||||
[CodeGen2.5](https://github.com/salesforce/CodeGen) is a family of autoregressive language models for **program synthesis**.
|
||||
|
||||
Building upon [CodeGen2](https://arxiv.org/abs/2305.02309), the model is trained on [StarCoderData](https://huggingface.co/datasets/bigcode/starcoderdata) for 1.4T tokens, achieving competitive results compared to StarCoderBase-15.5B with less than half the size.
|
||||
|
||||
Like CodeGen2, this model is capable of infilling, and supports multiple programming languages.
|
||||
|
||||
We then further train on Python, then on instruction data. We release all the models as follows:
|
||||
|
||||
* **CodeGen2.5-7B-multi** (this repo): Trained on StarCoderData. Licensed under Apache-2.0.
|
||||
* **CodeGen2.5-7B-mono**: Further trained on additional Python tokens. Licensed under Apache-2.0.
|
||||
* **CodeGen2.5-7B-instruct**: Further trained from CodeGen2.5-7B-mono on instruction data. *Research purposes only*.
|
||||
|
||||
## How to use
|
||||
|
||||
This model can be easily loaded using the `AutoModelForCausalLM` functionality.
|
||||
|
||||
### Pre-requisite
|
||||
|
||||
Please install OpenAI `tiktoken` for the tokenizer.
|
||||
|
||||
```bash
|
||||
pip install tiktoken==0.4.0
|
||||
```
|
||||
|
||||
### Causal sampling (code autocompletion)
|
||||
|
||||
For regular causal sampling, simply generate completions given the context:
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen25-7b-multi", trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen25-7b-multi")
|
||||
|
||||
text = "def hello_world():"
|
||||
input_ids = tokenizer(text, return_tensors="pt").input_ids
|
||||
generated_ids = model.generate(input_ids, max_length=128)
|
||||
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
### Infill sampling
|
||||
|
||||
For **infill** sampling, we follow the CodeGen2 format:
|
||||
|
||||
* `<mask_N>`: N-th span to be masked. In practice, use `<mask_1>` to where you want to sample infill.
|
||||
* `<sep>`: Separator token between the suffix and the infilled sample. See below.
|
||||
* `<eom>`: "End-Of-Mask" token that model will output at the end of infilling. You may use this token to truncate the output.
|
||||
|
||||
For example, if we want to generate infill for the following cursor position of a function:
|
||||
```python
|
||||
def hello_world():
|
||||
|
|
||||
return name
|
||||
```
|
||||
we construct an input to the model by
|
||||
|
||||
1. Inserting `<mask_1>` token in place of cursor position
|
||||
2. Append `<sep>` token to indicate the boundary
|
||||
3. Insert another `<mask_1>` to indicate which mask we want to infill.
|
||||
|
||||
The final snippet looks as follows:
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen25-7b-multi", trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen25-7b-multi")
|
||||
|
||||
|
||||
def format(prefix, suffix):
|
||||
return prefix + "<mask_1>" + suffix + "<|endoftext|>" + "<sep>" + "<mask_1>"
|
||||
|
||||
|
||||
prefix = "def hello_world():\n "
|
||||
suffix = " return name"
|
||||
text = format(prefix, suffix)
|
||||
input_ids = tokenizer(text, return_tensors="pt").input_ids
|
||||
generated_ids = model.generate(input_ids, max_length=128)
|
||||
print(tokenizer.decode(generated_ids[0], skip_special_tokens=False)[len(text):])
|
||||
```
|
||||
|
||||
You might want to truncate the model output with `<eom>`.
|
||||
|
||||
## Evaluation results
|
||||
|
||||
We evaluate our models on HumanEval and HumanEval-Infill.
|
||||
Please refer to the [blog](https://blog.salesforceairesearch.com/codegen25) for more details.
|
||||
|
||||
## Intended use and limitations
|
||||
|
||||
As an autoregressive language model, CodeGen2.5 is capable of extracting features from given natural language and programming language texts, and calculating the likelihood of them.
|
||||
However, the model is intended for and best at **program synthesis**, that is, generating executable code given English prompts, where the prompts should be in the form of a comment string. The model can complete partially-generated code as well.
|
||||
|
||||
## Attribution & Other Requirements
|
||||
The pretraining dataset of the model was filtered for permissive licenses only.
|
||||
Nevertheless, the model can generate source code verbatim from the dataset.
|
||||
The code's license might require attribution and/or other specific requirements that must be respected.
|
||||
The data provider BigCode provides a [search index](https://huggingface.co/spaces/bigcode/starcoder-search) that lets you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code.
|
||||
|
||||
## BibTeX entry and citation info
|
||||
|
||||
Please cite CodeGen2 paper:
|
||||
|
||||
```bibtex
|
||||
@article{Nijkamp2023codegen2,
|
||||
title={CodeGen2: Lessons for Training LLMs on Programming and Natural Languages},
|
||||
author={Nijkamp, Erik and Hayashi, Hiroaki and Xiong, Caiming and Savarese, Silvio and Zhou, Yingbo},
|
||||
journal={arXiv preprint},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
22
config.json
Normal file
22
config.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.29.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.29.2"
|
||||
}
|
||||
3
ggml-model-Q4_K.gguf
Normal file
3
ggml-model-Q4_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a33eb6211c79e25d2c179614e04be6b734070a8d097e9ab22def3a19c1472c7d
|
||||
size 4190013312
|
||||
3
ggml-model-f16.gguf
Normal file
3
ggml-model-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea6e9c8d6418ba85178e0c0f3547087196dcc008333844c8e61cd80bf33c5b57
|
||||
size 13792937824
|
||||
3
ggml-model-f32.gguf
Normal file
3
ggml-model-f32.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c8bae4d623525c0cc749c4398a153c8717557ccd676a5a9ee0511c1ae42577ec
|
||||
size 27583809376
|
||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 27582816256
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
||||
}
|
||||
}
|
||||
247
tokenization_codegen25.py
Normal file
247
tokenization_codegen25.py
Normal file
@@ -0,0 +1,247 @@
|
||||
# Copyright (c) 2023, salesforce.com, inc.
|
||||
# All rights reserved.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/Apache-2.0
|
||||
"""Tokenization classes for CodeGen2.5."""
|
||||
|
||||
from typing import List, Optional, Union
|
||||
|
||||
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
|
||||
from transformers.utils import logging
|
||||
|
||||
try:
|
||||
import tiktoken
|
||||
except ModuleNotFoundError as e:
|
||||
raise ModuleNotFoundError("CodeGen2.5 requires the installation of tiktoken. Please install it via `pip install tiktoken`.") from e
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
MAX_MODEL_INPUT_SIZES = {
|
||||
"Salesforce/codegen25-7b-multi": 2048,
|
||||
"Salesforce/codegen25-7b-mono": 2048,
|
||||
"Salesforce/codegen25-7b-instruct": 2048,
|
||||
}
|
||||
|
||||
|
||||
def tiktoken_tokenizer(base="gpt2", pad_token=None, add_special=True):
|
||||
if not add_special:
|
||||
return tiktoken.get_encoding(base)
|
||||
|
||||
def include_whitespace(n_min=2, n_max=20):
|
||||
whitespaces = [" " * n for n in reversed(range(n_min, n_max))]
|
||||
return whitespaces
|
||||
|
||||
def include_tabs(n_min=2, n_max=20):
|
||||
tabs = ["\t" * n for n in reversed(range(n_min, n_max))]
|
||||
return tabs
|
||||
|
||||
def include_fim_tokens():
|
||||
fim_tokens = [
|
||||
"<fim_prefix>",
|
||||
"<fim_middle>",
|
||||
"<fim_suffix>",
|
||||
"<fim_pad>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<empty_output>",
|
||||
"<commit_before>",
|
||||
"<commit_msg>",
|
||||
"<commit_after>",
|
||||
"<reponame>"
|
||||
]
|
||||
return fim_tokens
|
||||
|
||||
def include_codegen2_tokens():
|
||||
tokens = []
|
||||
tokens += [f"<dummy_{i}>" for i in range(4)]
|
||||
tokens.append("<sep>") # 50317
|
||||
tokens.append("<eom>") # 50318
|
||||
tokens += [f"<mask_{i}>" for i in reversed(range(1, 51199-50318+1))]
|
||||
return tokens
|
||||
|
||||
add_whitespaces = include_whitespace(n_min=2, n_max=32)
|
||||
add_tabs = include_tabs(n_min=2, n_max=10)
|
||||
fim_tokens = include_fim_tokens()
|
||||
codegen2_tokens = include_codegen2_tokens()
|
||||
|
||||
tokenizer = tiktoken.get_encoding(base)
|
||||
|
||||
idx = tokenizer.n_vocab
|
||||
|
||||
bpe_ranks = tokenizer._mergeable_ranks
|
||||
|
||||
for wsp in add_whitespaces:
|
||||
bpe_ranks[bytes(wsp, 'ascii')] = idx
|
||||
idx += 1
|
||||
for t in add_tabs:
|
||||
bpe_ranks[bytes(t, 'ascii')] = idx
|
||||
idx += 1
|
||||
|
||||
special_tokens = dict()
|
||||
|
||||
for sp in fim_tokens:
|
||||
special_tokens[sp] = idx
|
||||
idx += 1
|
||||
for sp in codegen2_tokens:
|
||||
special_tokens[sp] = idx
|
||||
idx += 1
|
||||
|
||||
if pad_token and pad_token not in tokenizer._special_tokens and pad_token not in special_tokens:
|
||||
special_tokens[pad_token] = idx
|
||||
idx += 1
|
||||
# In production, load the arguments directly instead of accessing private attributes
|
||||
# See openai_public.py for examples of arguments for specific encodings
|
||||
enc = tiktoken.Encoding(
|
||||
# If you're changing the set of special tokens, make sure to use a different name
|
||||
# It should be clear from the name what behaviour to expect.
|
||||
name=base.replace("base", "im"),
|
||||
pat_str=tokenizer._pat_str,
|
||||
mergeable_ranks=bpe_ranks,
|
||||
special_tokens={
|
||||
**tokenizer._special_tokens,
|
||||
**special_tokens
|
||||
}
|
||||
)
|
||||
return enc
|
||||
|
||||
|
||||
class CodeGen25Tokenizer(PreTrainedTokenizer):
|
||||
"""
|
||||
Construct a CodeGen2.5 tokenizer. Based on byte-level Byte-Pair-Encoding.
|
||||
Args:
|
||||
vocab_file (`str`):
|
||||
Path to the vocabulary file.
|
||||
"""
|
||||
max_model_input_sizes = MAX_MODEL_INPUT_SIZES
|
||||
model_input_names = ["input_ids", "attention_mask"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
pad_token=None,
|
||||
eos_token="<|endoftext|>",
|
||||
add_eos_token=False,
|
||||
add_special_tokens=True,
|
||||
**kwargs,
|
||||
):
|
||||
pad_token_added = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
|
||||
eos_token_added = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
|
||||
super().__init__(
|
||||
pad_token=pad_token_added,
|
||||
eos_token=eos_token_added,
|
||||
add_eos_token=add_eos_token,
|
||||
add_special_tokens=add_special_tokens,
|
||||
**kwargs,
|
||||
)
|
||||
self.add_eos_token = add_eos_token
|
||||
self.encoder = tiktoken_tokenizer(base="gpt2", pad_token=pad_token, add_special=add_special_tokens)
|
||||
|
||||
@property
|
||||
def vocab_size(self):
|
||||
"""Returns vocab size"""
|
||||
return self.encoder.n_vocab
|
||||
|
||||
def get_vocab(self):
|
||||
"""Returns vocab as a dict"""
|
||||
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
||||
return vocab
|
||||
|
||||
def _tokenize(self, text, **kwargs):
|
||||
"""Returns a tokenized string."""
|
||||
return self.encoder.encode(text, allowed_special="all")
|
||||
|
||||
def _convert_token_to_id(self, token):
|
||||
"""Converts a token (str) in an id using the vocab."""
|
||||
if isinstance(token, str):
|
||||
return self.encoder.encode_single_token(token)
|
||||
else:
|
||||
return token
|
||||
|
||||
def _convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
return self.encoder.decode_single_token_bytes(index).decode("utf-8")
|
||||
|
||||
def _decode(self, token_ids: Union[int, List[int]], skip_special_tokens: bool = False, **kwargs):
|
||||
if isinstance(token_ids, int):
|
||||
token_ids = [token_ids]
|
||||
if skip_special_tokens:
|
||||
token_ids = [t for t in token_ids if t not in self.all_special_ids]
|
||||
return self.encoder.decode(token_ids)
|
||||
|
||||
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None) -> List[int]:
|
||||
"""Build model inputs from a sequence by appending eos_token_id."""
|
||||
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
||||
|
||||
output = token_ids_0 + eos_token_id
|
||||
|
||||
if token_ids_1 is not None:
|
||||
output = output + 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 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
|
||||
)
|
||||
|
||||
eos_token_id = [1] if self.add_eos_token else []
|
||||
|
||||
if token_ids_1 is None:
|
||||
return ([0] * len(token_ids_0)) + eos_token_id
|
||||
return ([0] * len(token_ids_0)) + eos_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).
|
||||
"""
|
||||
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
||||
|
||||
output = [0] * len(token_ids_0 + eos_token_id)
|
||||
|
||||
if token_ids_1 is not None:
|
||||
output += [1] * len(token_ids_1 + eos_token_id)
|
||||
|
||||
return output
|
||||
|
||||
# has no vocab file
|
||||
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None):
|
||||
return ()
|
||||
12
tokenizer_config.json
Normal file
12
tokenizer_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"add_eos_token": false,
|
||||
"add_special_tokens": true,
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"tokenizer_class": "CodeGen25Tokenizer",
|
||||
"auto_map": {
|
||||
"AutoTokenizer": ["tokenization_codegen25.CodeGen25Tokenizer", null]
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user