Downloads · 30 days
2
5% of all-time downloads
AceGPT-7B-alpagasus_ar
Deema/AceGPT-7B-alpagasus_ar
AceGPT-7B-alpagasus_ar is a text generation model from Deema. Use it when you need the model to write or continue text. It is set up for peft.
The following bitsandbytes quantization config was used during training: - loadin8bit: True - loadin4bit: False - llmint8threshold: 6.0 - llmint8skipmodules: None - llmint8enablefp32cpuoffload: False - llmint8hasfp16w…
All-time downloads
42
Public
Repo size
34.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin33.6 MB · 93%
At a glance
- Task
- Text Generation
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Jan 12, 2024
- Updated
- Jan 12, 2024
- SHA
- 4547a45c
Datasets
Model card
From the Hugging Face model README
Training procedure
The following bitsandbytes quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
Framework versions
- PEFT 0.4.0
- Task
- Text Generation
- Library
- peft
- Type
- llama
- Languages
- ar
- Created
- Jan 12, 2024
- Updated
- Jan 12, 2024