Hugging Face's logo

Technotech
/
sd-prompt-instruct-3b-epoch-0.4-lora

PEFT
English
stable-diffusion
instruct
magic-prompt
Model card Files Community
1
sd-prompt-instruct-3b-epoch-0.4-lora / README.md
Technotech's picture
Technotech
Librarian Bot: Add base_model information to model (#1)
d32f010
preview code
|
raw
history blame contribute delete
799 Bytes
metadata
language:
  - en
license: apache-2.0
library_name: peft
tags:
  - stable-diffusion
  - instruct
  - magic-prompt
datasets:
  - Technotech/sd-prompt-instruct
base_model: openlm-research/open_llama_3b_v2

Stable Diffusion Prompt Instruct 3B (OpenLlama v2 3B)

Trained for 0.4 epochs (test) on Technotech/sd-prompt-instruct.

Training procedure

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: fp4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: float32

Framework versions

  • PEFT 0.5.0.dev0