Model Card for Model ID

์•„์ง Study ์ค‘์ธ ๋ฉ€ํ‹ฐ ํ„ด ์ฑ—๋ด‡ ๋ชจ๋ธ.

Model Details

Model Description

์ด์ „ ๋Œ€ํ™”์™€ ํ˜„์žฌ ๋Œ€ํ™”์˜ ๋ช…๋ น์–ด๋ฅผ ์ฐธ๊ณ ํ•˜์—ฌ ์ƒํ™ฉ์— ๊ณต๊ฐํ•˜๊ณ  ์นœ์ ˆํ•œ ์‘๋‹ต์„ ์ƒ์„ฑํ•ด์ฃผ์„ธ์š”. ์‘๋‹ต ๋งˆ์ง€๋ง‰์—๋Š” ์ง€๊ธˆ๊นŒ์ง€์˜ ๋‚ด์šฉ๊ณผ ๊ด€๋ จ๋œ ์งˆ๋ฌธ์„ ํ•ด์ฃผ์„ธ์š”.

[์ด์ „ ๋Œ€ํ™”] {}

[ํ˜„์žฌ ๋Œ€ํ™”]

๋ช…๋ น์–ด:

{}

์‘๋‹ต:

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 0.6.2
Downloads last month
2
Inference API
Unable to determine this modelโ€™s pipeline type. Check the docs .

Model tree for oosij/llama-2-ko-7b-ft-emo-multi

Adapter
(19)
this model