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

Dictalm2.0 by dicta-il

 »  All LLMs  »  dicta-il  »  Dictalm2.0   URL Share it on

  18017   
  Arxiv:2407.07080   Autotrain compatible   En   Endpoints compatible   He   Mistral   Pretrained   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dicta-il/dictalm2.0 

Dictalm2.0 Benchmarks

MMLU Pro: 17.83
GPQA: 5.59
MUSR: 5.51
BBH: 16.49
IFEval: 24.13 vs 88 (so35)-72.6%
MATH Lvl 5: 1.81
LLME Score: 0.26626
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dictalm2.0 (dicta-il/dictalm2.0)

Dictalm2.0 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
text generation
Limitations:
no moderation mechanisms
Additional Notes 
DictaLM-2.0 is a pretrained base model specifically designed to specialize in Hebrew text.
Supported Languages 
en (proficient), he (proficient)
Training Details 
Data Volume:
over 190B tokens
Methodology:
extended tokenizer with 1,000 injected tokens for Hebrew
Model Architecture:
Mistral-7B-v0.1 with enhancements for the Hebrew language
Input Output 
Accepted Modalities:
text
Output Format:
generated text
LLM NameDictalm2.0
Repository 🤗https://huggingface.co/dicta-il/dictalm2.0 
Model Size7.3b
Required VRAM14.5 GB
Updated2025-02-22
Maintainerdicta-il
Model Typemistral
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen he
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size33152
Torch Data Typebfloat16

Quantized Models of the Dictalm2.0

Model
Likes
Downloads
VRAM
Dictalm2.0 Instruct GGUF53244 GB
Dictalm2.0 Instruct AWQ02294 GB
Dictalm2.0 Instruct GPTQ01504 GB

Best Alternatives to Dictalm2.0

Best Alternatives
Context / RAM
Downloads
Likes
Dictalm2.0 Instruct32K / 14.5 GB1455819
Dictalm2 It Qa Fine Tune32K / 14.5 GB83473
Dictalm2.0 Instruct Fine Tuned32K / 14.5 GB55520
... Fine Tuned Alpaca Gpt4 Hebrew32K / 14.5 GB41900
Mis32K / 14.6 GB60
Misjava Api 060924 V3 Merged32K / 14.6 GB60
Quietstar 8 Ahead32K / 14.5 GB17890
Swallow Hermes St V14K / 14.6 GB2414
Note: green Score (e.g. "73.2") means that the model is better than dicta-il/dictalm2.0.

Rank the Dictalm2.0 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? 43470 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 v20241227
  Support LLM Explorer