Rexe
/

Deci-Decicoder-1b-lora-coder

Model card Files Files and versions Community

Rexe commited on Sep 17, 2023

Commit

310f94d

•

1 Parent(s): 95ec245

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -12,7 +12,6 @@ The following `bitsandbytes` quantization config was used during training:
 - llm_int8_skip_modules: None
 - llm_int8_enable_fp32_cpu_offload: False
 - llm_int8_has_fp16_weight: False
-- inference: true
 - bnb_4bit_quant_type: fp4
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float32

 - llm_int8_skip_modules: None
 - llm_int8_enable_fp32_cpu_offload: False
 - llm_int8_has_fp16_weight: False
 - bnb_4bit_quant_type: fp4
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float32