Hugging Face's logo

mychen76
/
codellama-7b-text-to-sql

PEFT
PyTorch
llama
8-bit precision
bitsandbytes
Model card Files Community

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: True
  • bnb_4bit_compute_dtype: float16

Framework versions

  • PEFT 0.5.0
Downloads last month
5
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Collection including mychen76/codellama-7b-text-to-sql