Dictalm2.0 GPTQ by dicta-il

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

Dictalm2.0 GPTQ is an open-source language model by dicta-il. Features: 7.3b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  Arxiv:2407.07080   4-bit   En   Gptq   He   Mistral   Pretrained   Quantized   Region:us   Safetensors

Dictalm2.0 GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Dictalm2.0 GPTQ Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications involving Hebrew text
Applications:
Hebrew text processing, Instruction capabilities in Hebrew
Primary Use Cases:
Text generation in Hebrew
Limitations:
No moderation mechanisms
Additional Notes 
Default version does not include moderation mechanisms.
Supported Languages 
en (Supported), he (Primary support)
Training Details 
Data Sources:
Hebrew text, General text data for foundational training
Data Volume:
Not specified
Methodology:
Extended tokenizer with 1,000 Hebrew-specific tokens
Model Architecture:
Based on the Mistral-7B-v0.1 with extended tokenizer for Hebrew
Input Output 
Accepted Modalities:
text
LLM NameDictalm2.0 GPTQ
Repository 🤗https://huggingface.co/dicta-il/dictalm2.0-GPTQ 
Model Size7.3b
Required VRAM4.2 GB
Updated2026-05-07
Maintainerdicta-il
Model Typemistral
Model Files  4.2 GB
Supported Languagesen he
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size33152
Torch Data Typebfloat16

Best Alternatives to Dictalm2.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Dictalm2.0 Instruct GPTQ32K / 4.2 GB240
Dictalm2.0 Instruct32K / 14.5 GB770825
Dictalm2.032K / 14.5 GB632128
My Tokenizer 100 1000032K / 22.3 GB60
My Tokenizer 50 2000032K / 14.6 GB50
Dictalm2.0 Instruct Fine Tuned32K / 14.5 GB66420
... Fine Tuned Alpaca Gpt4 Hebrew32K / 14.5 GB53650
Mis32K / 14.6 GB60
Dictalm2 It Qa Fine Tune32K / 14.5 GB12097
Misjava Api 060924 V3 Merged32K / 14.6 GB70
Note: green Score (e.g. "73.2") means that the model is better than dicta-il/dictalm2.0-GPTQ.

Rank the Dictalm2.0 GPTQ 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? 53999 in total.

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