| library_name: peft | |
| base_model: meta-llama/Llama-2-7b-hf | |
| # Fine-Tuned Llama-2-7b-hf Model | |
| This is a fine-tuned version of the Llama-2-7b-hf model, customized for specific tasks. | |
| - Model architecture: Llama-2-7b-hf | |
| - Fine-tuning details: This model was finetunned to generate reponses to specific task. | |
| - Usage: You can load this model with Hugging Face Transformers. | |
| Feel free to add more details as needed. | |
| ## 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: nf4 | |
| - bnb_4bit_use_double_quant: True | |
| - bnb_4bit_compute_dtype: float16 | |
| ### Framework versions | |
| - PEFT 0.5.0 | |