|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
library_name: peft |
|
base_model: tiiuae/falcon-rw-1b |
|
datasets: |
|
- MichaelAI23/hotel_requests |
|
--- |
|
## Training procedure |
|
|
|
This is a Falcon 1B model that was finetuned on the MichaelAI23/hotel_requests dataset. |
|
LoRA was used for the training in combination with 8-bit quantization. |
|
|
|
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 0.6.0.dev0 |
