dolphin-cyber-arabic is an open-weight model from Khaled hamdan. Its published files total 92.2 MB.
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct. It has been trained using TRL. This model was trained with SFT.
Parameters—
Context—
Weights80.8 MB
License—
AccessOpen weights
Monthly Downloads—
Model Card
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by Khaled hamdan.
Identity and Version
- Repository
- Koko12345p/dolphin-cyber-arabic
- Publisher
- Khaled hamdan
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- trl, sft
- Revision
- 043b7c33ea298e17c72ddb6e7a91846b0c3367a2
- First published
- 2026-09-19
- Last updated
- 2026-09-20
Files and Weights
8 files, 92.2 MB in total. The weights are 2 files totalling 80.8 MB in bin, safetensors.
Weights2 files · 80.8 MB
Configuration1 file · 1.2 KB
Tokenizer2 files · 11.4 MB
Documentation1 file · 1.4 KB
Other1 file · 2.5 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 80.8 MB | bab303fe3114 |
| training_args.bin | Weights | 5.8 KB | 2cd5140ddbba |
| adapter_config.json | Configuration | 1.2 KB | — |
| README.md | Documentation | 1.4 KB | — |
| chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| tokenizer_config.json | Tokenizer | 691 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 80.8 MB
Download from Khaled hamdan
Released by Khaled hamdan through its official repository on Hugging Face.
Built From
- Derived from Qwen/Qwen2.5-7B-Instruct
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 80.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.