A full SFT of original 'llama-2-13b_code-alpaca' using a mix of English and Serbian instruction data.
The following bitsandbytes quantization config was used during training: 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: bfloat16
The following bitsandbytes quantization config was used during training: 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: bfloat16
The following bitsandbytes quantization config was used during training: 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: bfloat16
Framework versions PEFT 0.5.0.dev0