Arxiv:2407.10671 4bit Ar Arabic Conversational Dira Instruct Lora Peft Quantized Qwen Reasoning Region:us Safetensors Unsloth
Model Card on HF 🤗: https://huggingface.co/Omartificial-Intelligence-Space/Diraya-3B-Instruct-Ar
Diraya 3B Instruct Ar Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Diraya 3B Instruct Ar Parameters and Internals
| LLM Name | Diraya 3B Instruct Ar |
| Repository 🤗 | https://huggingface.co/Omartificial-Intelligence-Space/Diraya-3B-Instruct-Ar |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 0 GB |
| Updated | 2025-05-16 |
| Maintainer | Omartificial-Intelligence-Space |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ar |
| Quantization Type | 4bit |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|gate_proj|o_proj|down_proj|v_proj|up_proj|q_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 64 |
| Errors | replace |
Best Alternatives to Diraya 3B Instruct Ar
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen 2.5 3B R1 Lora Model V.1 | 0K / 0.1 GB | 0 | 1 |
| Llama 3.2 3B R1 Lora | 0K / 0.1 GB | 0 | 2 |
| Llama 3.2 3B Smart V1 Lora | 0K / 0.1 GB | 0 | 1 |
| ...lama 3.2 3B General Lora Model | 0K / 0.1 GB | 0 | 1 |
| Llama 3.2 3B Code Lora Model | 0K / 0.1 GB | 0 | 2 |
| Qwen 2.5 3B Rp Lora Model | 0K / 0.1 GB | 0 | 3 |
| Llama 3.2 3B Lora Model | 0K / 0.1 GB | 0 | 4 |
| Qwen 2.5 3B Rp Mix Lora | 0K / 0.1 GB | 0 | 1 |
| Llama 3.2 3B RP LORA | 0K / 0.1 GB | 0 | 1 |
| Llama 3.2 3B VanRossum | 0K / 6.5 GB | 61 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Omartificial-Intelligence-Space/Diraya-3B-Instruct-Ar .
Rank the Diraya 3B Instruct Ar 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! 🌟
What open-source LLMs or SLMs are you in search of? 47377 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227