LLM EXPLORER 60,702 MODELS INDEXED

Dictalm2.0 Instruct Fine Tuned Alpaca Gpt4 Hebrew by ronigold

By ronigold · 201 downloads
HF Repo ↗ Copy URL

Dictalm2.0 Instruct Fine Tuned Alpaca Gpt4 Hebrew is an open-source language model by ronigold. Features: 7.3b LLM, VRAM: 14.5GB, Context: 32K, License: mit, Instruction-Based, Merged, LLM Explorer Score: 0.12.

  Merged Model   Conversational   Deploy:azure   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ronigold/dictalm2.0-instruct-fine-tuned-alpaca-gpt4-hebrew 

Dictalm2.0 Instruct Fine Tuned Alpaca Gpt4 Hebrew Parameters and Internals

Model Type 
Transformer-based, fine-tuned
Use Cases 
Areas:
Educational, Informational applications
Primary Use Cases:
Generating contextual question-answer pairs from textual content
Limitations:
Not intended for factual accuracy in critical areas like medical or legal advice
Additional Notes 
The model is part of a broader initiative to enhance NLP capabilities in the Hebrew language.
Supported Languages 
Hebrew (High)
Training Details 
Data Sources:
Synthetic dataset generated from Hebrew Wikipedia
Methodology:
Specific loss functions and optimization strategies used for fine-tuning.
Hardware Used:
NVIDIA Tesla V100s
Model Architecture:
Transformer-based architecture with optimizations for question generation and answering.
Responsible Ai Considerations 
Mitigation Strategies:
Use with human oversight for accuracy and appropriateness in sensitive applications.
LLM NameDictalm2.0 Instruct Fine Tuned Alpaca Gpt4 Hebrew
Repository 🤗https://huggingface.co/ronigold/dictalm2.0-instruct-fine-tuned-alpaca-gpt4-hebrew 
Merged ModelYes
Model Size7.3b
Required VRAM14.5 GB
Updated2026-08-06
Maintainerronigold
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.38.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size33152
Torch Data Typefloat16

Best Alternatives to Dictalm2.0 Instruct Fine Tuned Alpaca Gpt4 Hebrew

Best Alternatives
Context / RAM
Downloads
Likes
Dictalm2.0 Instruct32K / 14.5 GB279125
Dictalm2 It Qa Fine Tune32K / 14.5 GB267
Dictalm2.0 Instruct Fine Tuned32K / 14.5 GB210
Dictalm2.0 Instruct AWQ32K / 4.2 GB930
Dictalm2.0 Instruct GPTQ32K / 4.2 GB60
Note: green Score (e.g. "73.2") means that the model is better than ronigold/dictalm2.0-instruct-fine-tuned-alpaca-gpt4-hebrew.