LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Law Chat by AdaptLLM

 »  All LLMs  »  AdaptLLM  »  Law Chat   URL Share it on

  599   
  Arxiv:2309.09530   Arxiv:2406.14491   Arxiv:2411.19930   Autotrain compatible   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 Benchmarks

ARC: 53.41 vs 96.7 (so35)-44.8%
HellaSwag: 76.16 vs 95.3 (gpt4)-20.1%
MMLU: 50.24 vs 88.3 (so35)-43.1%
TruthfulQA: 43.53 vs 59 (gpt4)-26.2%
WinoGrande: 75.45 vs 87.5 (gpt4)-13.8%
GSM8K: 18.5 vs 96.4 (so35)-80.8%
LLME Score: 0.17582
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

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 NameLaw Chat
Repository 🤗https://huggingface.co/AdaptLLM/law-chat 
Model Size6.7b
Required VRAM27 GB
Updated2025-06-09
MaintainerAdaptLLM
Model Typellama
Instruction-BasedYes
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 Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Padding Token<pad>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat16
Law Chat (AdaptLLM/law-chat)

Quantized Models of the Law Chat

Model
Likes
Downloads
VRAM
Law Chat GGUF214992 GB
Law Chat AWQ3883 GB
Law Chat GPTQ4303 GB

Best Alternatives to Law Chat

Best Alternatives
Context / RAM
Downloads
Likes
...s Coder6.7b Reflct Adamw Iter116K / 13.5 GB4750
...Coder6.7b Reflct Rmsprop Iter116K / 13.5 GB950
...Coder6.7b Reflct Rmsprop Iter116K / 13.5 GB1100
...r6.7b Pos Reflct Rmsprop Iter116K / 13.5 GB870
...r6.7b Pos Reflct Rmsprop Iter116K / 13.5 GB900
...ir4 Ds Coder6.7b Rmsprop Iter116K / 13.5 GB430
Ds Coder6.7b Rmsprop Iter116K / 13.5 GB670
...Coder6.7b Reflct Rmsprop Iter116K / 13.5 GB620
Speechless Coder Ds 6.7B16K / 13.5 GB2186
Magicoder S DS 6.7B16K / 27.1 GB1004203
Note: green Score (e.g. "73.2") means that the model is better than AdaptLLM/law-chat.

Rank the Law Chat Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 48023 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer