What are the hardware requirements for Law Chat?

Law Chat requires approximately 27 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Law Chat and how large is it?

Law Chat is developed by AdaptLLM, a model with 6.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Law Chat perform on standard benchmarks?

Law Chat has the following published scores: MMLU 50.24. Compare against reference models on this page or on the LLM Explorer leaderboards.

Law Chat by AdaptLLM — VRAM 27GB, 4K context

Name: Law Chat
Author: AdaptLLM

Law Chat is an open-source language model by AdaptLLM. Features: 6.7b LLM, VRAM: 27GB, Context: 4K, License: llama2, Instruction-Based, LLM Explorer Score: 0.13, Arc: 53.4, HellaSwag: 76.2, MMLU: 50.2, GSM8K: 18.5.

Arxiv:2309.09530 Arxiv:2406.14491 Arxiv:2411.19930 Dataset:eleutherai/pile Dataset:gair/lima Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol... En Endpoints compatible Instruct Legal Llama Model-index Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/AdaptLLM/law-chat

Law Chat Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

Legal domain

Additional Notes

Continual pre-training on domain-specific corpora helps enrich domain knowledge but can degrade question answering prompting ability.

Training Details

Data Sources:

EleutherAI/pile, Open-Orca/OpenOrca, GAIR/lima, WizardLM/WizardLM_evol_instruct_V2_196k

Methodology:

Continued pre-training on domain-specific corpora using reading comprehension transformation method

Release Notes

Date:

2023/12/8

Notes:

Released chat models developed from LLaMA-2-Chat-7B

LLM Name	Law Chat
Repository 🤗	https://huggingface.co/AdaptLLM/law-chat
Model Size	6.7b
Required VRAM	27 GB
Updated	2026-08-24
Maintainer	AdaptLLM
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 7.2 GB: 3-of-3 9.9 GB: 1-of-3 9.9 GB: 2-of-3 7.2 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Padding Token	<pad>
Unk Token	<unk>
Vocabulary Size	32001
Torch Data Type	float16

Rank the Law Chat capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Law Chat

Model	Likes	Downloads	VRAM
Law Chat GGUF	25	714	2 GB
Law Chat AWQ	4	7	3 GB
Law Chat GPTQ	4	5	3 GB

Best Alternatives to Law Chat

Best Alternatives	Context / RAM	Downloads	Likes
Speechless Coder Ds 6.7B	16K / 13.5 GB	459	7
...s Coder6.7b Reflct Adamw Iter1	16K / 13.5 GB	475	0
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	95	0
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	110	0
...r6.7b Pos Reflct Rmsprop Iter1	16K / 13.5 GB	87	0
...ir4 Ds Coder6.7b Rmsprop Iter1	16K / 13.5 GB	43	0
...r6.7b Pos Reflct Rmsprop Iter1	16K / 13.5 GB	90	0
Code 290K 6.7B Instruct	16K / 13.5 GB	87	6
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	62	0
Ds Coder6.7b Rmsprop Iter1	16K / 13.5 GB	67	0

Note: green Score (e.g. "73.2") means that the model is better than AdaptLLM/law-chat.