SaulLM Models by Equall
About
The SaulLM family is a collection of large language models specifically crafted for the legal domain, with the foundational SaulLM-7B model comprising 7 billion parameters. Initially trained on an extensive English legal corpus of over 30 billion tokens, the SaulLM-7B model was further refined through advanced pretraining and instruction fine-tuning to produce SaulLM-7B-Instruct, which is optimized for instruction-following tasks within the legal sector. Following the original model's success, the family expanded with the introduction of larger models like SaulLM-54B and SaulLM-141B, incorporating 54 billion and 141 billion parameters, respectively. These models feature the Mixtral architecture and focus on refined domain adaptation, including continued pretraining on a vast legal dataset exceeding 540 billion tokens. Deployed with specialized instruction protocols and aligned with human legal interpretation preferences, all models in the SaulLM family support open collaboration through a permissive MIT license, fostering innovation within the legal AI community 12356.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs legal, 66k context, and 141B parameters.
Use when the workload needs legal, 33k context, and 54B parameters.
Use when the workload needs legal, 66k context, and 141B parameters.
Use when the workload needs legal, 33k context, and 54B parameters.
Use when the workload needs legal, 33k context, and 7B parameters.
Use when the workload needs legal, 33k context, and 7B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Saul 141B | Use when the workload needs legal, 66k context, and 141B parameters. | 2024-07 | legal66k context141B parameters | Current |
| Saul 54B | Use when the workload needs legal, 33k context, and 54B parameters. | 2024-07 | legal33k context54B parameters | Current |
| Saul 141B Instruct | Use when the workload needs legal, 66k context, and 141B parameters. | 2024-07 | legal66k context141B parameters | Current |
| Saul 54B Instruct | Use when the workload needs legal, 33k context, and 54B parameters. | 2024-07 | legal33k context54B parameters | Current |
| Saul 7B Instruct | Use when the workload needs legal, 33k context, and 7B parameters. | 2024-03 | legal33k context7B parameters | Current |
| Saul 7B | Use when the workload needs legal, 33k context, and 7B parameters. | 2024-02 | legal33k context7B parameters | Current |
Release Timeline
3 release groupsSpecifications(6 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Saul 141B | 2024-07 | 66k | 141B |
| Saul 54B | 2024-07 | 33k | 54B |
| Saul 141B Instruct | 2024-07 | 66k | 141B |
| Saul 54B Instruct | 2024-07 | 33k | 54B |
| Saul 7B Instruct | 2024-03 | 33k | 7B |
| Saul 7B | 2024-02 | 33k | 7B |
Frequently Asked Questions
- What is SaulLM used for?
- SaulLM is used for legal. The family description and listed model capabilities point to those workloads as the best fit.
- How does SaulLM compare to Claude 3?
- SaulLM by Equall is strongest where you need legal, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. SaulLM has 6 listed variants and reaches up to 66k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which SaulLM model should I use?
- If price is the main constraint, use the pricing table first because SaulLM does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Saul 141B with 66k context.