|
--- |
|
library_name: peft |
|
base_model: mistralai/Mistral-7B-Instruct-v0.1 |
|
--- |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
This is a chat model specialized for SQL, |
|
which has been fine-tuned based on the 'Mistral-7B-Instruct-v0.1' using 'sql-create-context' datasets. |
|
|
|
SQLに特化したMistral-7Bモデルです（普段のクエリ書くために作りました、よろしければ試してみてください） |
|
|
|
## Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- quant_method: bitsandbytes |
|
- load_in_8bit: False |
|
- load_in_4bit: True |
|
- 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: nf4 |
|
- bnb_4bit_use_double_quant: False |
|
- bnb_4bit_compute_dtype: float16 |
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.0.dev0 |
|
|
