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

Dictalm2.0 Instruct by dicta-il

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

  7708   

Dictalm2.0 Instruct is an open-source language model by dicta-il. Features: 7.3b LLM, VRAM: 14.5GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

  Arxiv:2407.07080   Base model:dicta-il/dictalm2.0 Base model:finetune:dicta-il/d...   Conversational   Deploy:azure   En   Endpoints compatible   He   Instruct   Instruction-tuned   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dicta-il/dictalm2.0-instruct 

Dictalm2.0 Instruct Benchmarks

MMLU Pro: 17.83
GPQA: 7.05
MUSR: 9.72
BBH: 19.69
IFEval: 44.12 vs 88 (so35)-49.9%
MATH Lvl 5: 2.27
LLME Score: 0.21486
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dictalm2.0 Instruct (dicta-il/dictalm2.0-instruct)
🌟 Advertise your project 🚀

Dictalm2.0 Instruct Parameters and Internals

Model Type 
text-generation
Additional Notes 
This is an instruct fine-tuned version of DictaLM-2.0, using a variety of conversation datasets. It is designed primarily for chat applications, fine-tuned with an extended dataset for Hebrew.
Supported Languages 
Hebrew (native proficiency), English (support available)
Training Details 
Methodology:
Zephyr-7B-beta instruction fine-tuning
Model Architecture:
Zephyr-7B-beta recipe for fine-tuning an instruct model
Input Output 
Input Format:
[INST] and [/INST] tokens in prompts
Accepted Modalities:
text
Output Format:
text
LLM NameDictalm2.0 Instruct
Repository 🤗https://huggingface.co/dicta-il/dictalm2.0-instruct 
Base Model(s)  dicta-il/dictalm2.0   dicta-il/dictalm2.0
Model Size7.3b
Required VRAM14.5 GB
Updated2026-03-11
Maintainerdicta-il
Model Typemistral
Instruction-BasedYes
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 Version4.38.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size33152
Torch Data Typebfloat16

Best Alternatives to Dictalm2.0 Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Dictalm2.0 Instruct Fine Tuned32K / 14.5 GB55640
... Fine Tuned Alpaca Gpt4 Hebrew32K / 14.5 GB51460
Dictalm2 It Qa Fine Tune32K / 14.5 GB12097
Dictalm2.0 Instruct AWQ32K / 4.2 GB150
Dictalm2.0 Instruct GPTQ32K / 4.2 GB240

Rank the Dictalm2.0 Instruct 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer