alea-institute
/

kl3m-004-128k-cased

@@ -1,199 +1,170 @@
 ---
-library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+language:
+- en
+- es
+- fr
+- de
+library_name: tokenizers
+license: cc-by-4.0
+tags:
+- kl3m
+- kl3m-003
+- alea
+- legal
+- financial
+date: '2024-11-07T00:00:00.000Z'
 ---
+# kl3m-004-128k-cased tokenizer
+The `kl3m-004-128k-cased` **case-sensitive** tokenizer is a domain-specific tokenizer trained on a stratified sample of nearly 4M
+documents across general, legal, and financial domains from the `kl3m-data` project, including American English,
+British English, Spanish, German, French, Italian, and other common EU languages.
+This tokenizer is being used for the next generation of KL3M embedding and generative models.
+Please see `kl3m-001-32k` and `kl3m-003-64k` for the first iteration of our research on domain-specific tokenization.
+Note that we are providing both case and cased versions of the 128K tokenizer, unlike prior tokenizers, as this was
+required to achieve SotA in-domain performance for embedding models on legal and financial text.
+## Model Details
+### Summary
+- **Vocabulary**: 131,072
+- **Tokenizer type:** BPE
+- **Special token support:** Both causal and masked language modeling
+- **Language(s) (NLP):** Primarily English, Spanish, German, French, with a small percentage of other EU languages.
+- **Data Sources**: See [`kl3m-data`](https://github.com/alea-institute/kl3m-data) repository.
+- **Developed by:** [ALEA Institute](https://aleainstitute.ai).
+- **License:** [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/)
+### Model Description
+The `kl3m-004-128k-cased` tokenizer is a domain-specific tokenizer trained on ~1.5T tokens of financial and legal text from primarily-English sources.
+This tokenizer is notable for a number of reasons:
+#### Domain Specific
+As part of our research on more efficient SLM training for the legal and financial domain, we
+trained a domain-specific tokenizer on a large corpus of financial and legal text. This tokenizer
+has not, for example, seen any common general pretrain sources like Wikipedia or Common Crawl.
+#### Large Added Token Set
+As part of our research on efficient and reliable extraction and generation, we inserted
+a large numer of deterministic "whole" tokens into the tokenizer, such as HTML tags
+like `<span`, common Markdown elements like `#` and `##`, and legal enumerations like `(a)`.
+**Note that the kl3m-004-128k-cased tokenizer has added a number of additional citation formats that were not
+included in the kl3m-001-32k tokenizer.**  These were primarily sourced from empirical data and
+the [Free Law Project's reporters-db](https://raw.githubusercontent.com/freelawproject/reporters-db/main/reporters_db/data/),
+which were added to the tokenizer to improve model behavior related to legal citations.
+See the `get_custom_tokens` method in `kl3m_embeddings/training/kl3m_004/train_tokenizer.py` for
+more details:
+```python
+def get_custom_tokens(
+    include_whitespace: bool = True,
+    include_markdown: bool = True,
+    include_html: bool = True,
+    include_json: bool = True,
+    include_xml: bool = True,
+    include_years: bool = True,
+    include_citations: bool = True,
+    lowercase: bool = False,
+) -> list[str]:
+```
+#### Space Preservation
+Unlike `kl3m-001-32k`, we *do not* retain the space character as a token.  This was done after adding additional legal
+citation tokens to the vocabulary, which reduced the number of issues related to space tokenization in legal text.  This
+means that the `kl3m-004-128k-cased` tokenizer uses substantially fewer tokens than `kl3m-001-32k` for most text.
+#### Special Tokens for both Embedding and Generative Models
+For both training and inference efficiency, we intended this tokenizer vocabulary to be
+usable for both embedding and generative models. As such, we included special tokens
+suitable for both causal and masked language modeling tasks.
+* `<|start|>`: `0`
+* `<|end|>`: `1`
+* `<|pad|>`: `2`
+* `<|unk|>`: `3`
+* `<|sep|>`: `4`
+* `<|cls|>`: `5`
+* `<|mask|>`: `6`
+We also added a number of chat and instruction tokens that were not included in `kl3m-001-32k`, including:
+* `<|system|>`: `7`
+* `</|system|>`: `8`
+* `<|user|>`: `9`
+* `</|user|>`: `10`
+* `<|instruction|>`: `11`
+* `</|instruction|>`: `12`
+These tokens are identical to those used in the `kl3m-003-64k` tokenizer.
+### Replication
+The entire data collection and preprocesing pipeline is being made available, along with
+training data, as part of the [ALEA Institute](https://aleainstitute.ai) [KL3M project](https://aleainstitute.ai/work/kl3m/).
+The source code to used to train the tokenizer is available on GitHub at:
+[https://github.com/alea-institute/kl3m-embedding-research](https://github.com/alea-institute/kl3m-embedding-research)
+The data pipeline will be available on GitHub and S3 in the near future.
+## Uses
+This tokenizer is intended to be used for English, Spanish, German, or French language text in professional contexts
+such as legal and financial documents.
+### Recommendations
+In general, the `kl3m-004-128k-cased` tokenizer is recommended over the original `kl3m-001-32k` tokenizer.
+```text
+Original text:  The Comptroller of the Currency shall have the same authority with respect to functions transferred to the Comptroller of the Currency under the Enhancing Financial Institution Safety and Soundness Act of 2010 as was vested in the Director of the Office of Thrift Supervision on the transfer date, as defined in section 311 of that Act [12 U.S.C. 5411].
+kl3m-003-64
+-----------
+Size:  67
+Tokens:  ['The', ' Comptroller', ' of', ' the', ' Currency', ' shall', ' have', ' the', ' same', ' authority', ' with', ' respect', ' to', ' functions', ' transferred', ' to', ' the', ' Comptroller', ' of', ' the', ' Currency', ' under', ' the', ' Enh', 'ancing', ' Financial', ' Institution', ' Safety', ' and', ' ', 'Sound', 'ness', ' Act', ' of', ' 2010', ' as', ' was', ' vested', ' in', ' the', ' Director', ' of', ' the', ' Office', ' of', ' Thrift', ' Supervision', ' on', ' the', ' transfer', ' date', ',', ' as', ' defined', ' in', ' section', ' 311', ' of', ' that', ' Act', ' [', '12', ' ', 'U.S.C.', ' 54', '11', '].']
+IDs:  [671, 13273, 295, 281, 25922, 735, 704, 281, 1913, 2451, 440, 1894, 312, 5860, 7264, 312, 281, 13273, 295, 281, 25922, 621, 281, 18926, 4406, 3195, 24448, 5617, 310, 233, 63589, 2130, 854, 295, 1611, 398, 725, 11978, 300, 281, 2827, 295, 281, 1767, 295, 44029, 37141, 395, 281, 3696, 1548, 24, 398, 3011, 300, 782, 6590, 295, 407, 854, 1327, 524, 233, 63761, 3789, 547, 8578]
+kl3m-004-128k-cased
+---------------------
+Size:  65
+Tokens:  ['The', ' Comptroller', ' of', ' the', ' Currency', ' shall', ' have', ' the', ' same', ' authority', ' with', ' respect', ' to', ' functions', ' transferred', ' to', ' the', ' Comptroller', ' of', ' the', ' Currency', ' under', ' the', ' Enhancing', ' Financial', ' Institution', ' Safety', ' and', ' Sound', 'ness', ' Act', ' of', ' 2010', ' as', ' was', ' vested', ' in', ' the', ' Director', ' of', ' the', ' Office', ' of', ' Thrift', ' Supervision', ' on', ' the', ' transfer', ' date', ',', ' as', ' defined', ' in', ' section', ' 311', ' of', ' that', ' Act', ' [', '12', ' ', 'U.S.C.', ' 54', '11', '].']
+IDs:  [908, 21512, 290, 280, 8927, 462, 635, 280, 1552, 1788, 405, 893, 305, 5135, 4877, 305, 280, 21512, 290, 280, 8927, 563, 280, 62796, 2870, 15216, 4687, 310, 24831, 1486, 761, 290, 2446, 377, 637, 6341, 301, 280, 3422, 290, 280, 2379, 290, 36886, 29212, 401, 280, 1918, 819, 24, 377, 2024, 301, 984, 14706, 290, 388, 761, 747, 633, 233, 129009, 4090, 583, 4845]
+```
+## How to Get Started with the Model
+Use the code below to get started with the model.
+```
+from tokenizers import Tokenizer
+tokenizer = Tokenizer.from_pretrained('alea-institute/kl3m-004-128k-cased')
+```
+## Citation
+Tokenizer and dataset publications are pending.
+## Contact
+For any questions, please contact [ALEA Institute](https://aleainstitute.ai) at [hello@aleainstitute.ai](mailto:hello@aleainstitute.ai) or
+create an issue on this repository or [GitHub](https://github.com/alea-institute/kl3m-embedding-research).
+![logo](https://aleainstitute.ai/images/alea-logo-ascii-1x1.png)