YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
๐ค Thoth Text Model
๐ Overview
Thoth Text ูู ูู
ูุฐุฌ ูุบูู ุนุฑุจู ู
ุจูู ุนูู Qwen2.5-7B-Instruct
ุชู
ุชุฏุฑูุจู ุจุงุณุชุฎุฏุงู
ุชูููุฉ LoRA (Low-Rank Adaptation) ูุชุญุณูู ุงูุฃุฏุงุก ูู ููู
ุงููุตูุต ุงูุนุฑุจูุฉ
ูุชูููุฏ ุฅุฌุงุจุงุช ุฏูููุฉ ูู ุงูู
ุฌุงูุงุช ุงูุนุงู
ุฉ ูุงูุชุนููู
ูุฉ.
๐ง Base Model
- Base:
Qwen/Qwen2.5-7B-Instruct - Adapter: LoRA fine-tuned using Axolotl
- Architecture: Transformer Decoder (Causal LM)
- Precision:
bfloat16 - Frameworks: PyTorch + Transformers + PEFT
๐๏ธ Fine-tuning Details
- Library: Axolotl
- Adapter Type: LoRA
- Learning Rate:
2e-4 - LoRA ฮฑ:
16 - LoRA r:
8 - Dropout:
0.05 - Batch Size:
16 - Epochs:
1 - Optimizer:
adamw_bnb_8bit - Sequence Length:
4096 - Compute: RunPod GPU Instance
๐ Dataset
โ ๏ธ Note:
The dataset used for fine-tuning is private and locally stored at/workspace/fine-tuning/data/trump.jsonIt follows the Alpaca-style JSON format:
[
{
"instruction": "ุงุดุฑุญ ูู ู
ูููู
ุงูุฐูุงุก ุงูุงุตุทูุงุนู.",
"input": "",
"output": "ุงูุฐูุงุก ุงูุงุตุทูุงุนู ูู ูุฑุน ู
ู ุนููู
ุงูุญุงุณูุจ ููุชู
ุจุฌุนู ุงูุฃูุธู
ุฉ ูุงุฏุฑุฉ ุนูู ุงูุชูููุฑ ูุงูุชุนูู
."
}
]
- Downloads last month
- 8
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support