|
--- |
|
library_name: peft |
|
--- |
|
# LLAMA2 7B Guanaco Pico Adapter |
|
This is a 8Bit Quantized adapter over llama2-7b-chat-hf checkpoint. |
|
To use the merged version of this model refer: manojkumarvohra/llama2-7B-Chat-hf-8bit-guanaco-pico-finetuned => https://huggingface.co/manojkumarvohra/llama2-7B-Chat-hf-8bit-guanaco-pico-finetuned |
|
This is only meant for learning purpose and is not recommended to be used for any business purpose. |
|
|
|
## 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 |
|
|
|
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 |
|
|
|
- PEFT 0.4.0 |
