mwz
/

PEFT
Urdu
bnb
UrduOPT-2.7b-lora / README.md
librarian-bot's picture
Librarian Bot: Add base_model information to model
48efa64
|
raw
history blame
739 Bytes
---
language:
- ur
license: mit
library_name: peft
tags:
- bnb
datasets:
- anuragshas/ur_opus100_processed
widget:
- text: 'کیا ان لوگوں کا کہنا یہ '
- text: 'موسیٰؑ نے جواب دیا '
- text: 'اے لوگو اپنے رب سے ڈرو '
base_model: facebook/opt-2.7b
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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 0.5.0.dev0