Hugging Face's logo

BatsResearch
/
Llama-2-7b-hf-P3

PEFT
Model card Files Community
Llama-2-7b-hf-P3 / adapter_model /README.md
nihalnayak's picture
nihalnayak
Upload folder using huggingface_hub
5c7ee52 verified
preview code
|
raw
history blame contribute delete
1.63 kB

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: float32

Framework versions

  • PEFT 0.5.0 tion 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: float32

Framework versions

  • PEFT 0.5.0

  • PEFT 0.5.0 ing 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: float32

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: float32

Framework versions

  • PEFT 0.5.0

  • PEFT 0.5.0

  • PEFT 0.5.0