Downloads · 30 days
6
18% of all-time downloads
llama-recipe-7b-1epoch-8batch
mindreader/llama-recipe-7b-1epoch-8batch
llama-recipe-7b-1epoch-8batch is a machine learning model from mindreader. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
!python llama-recipes/llamafinetuning.py \ --usepeft \ --numepochs 1 \ --peftmethod lora \ --runvalidation false \ --quantization \ --dataset alpacadataset \ --modelname meta-llama/Llama-2-7b-chat-hf \ --savemodel \ -…
All-time downloads
34
Public
Repo size
13.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin13.5 GB · 100%
At a glance
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Aug 15, 2023
- Updated
- Aug 16, 2023
- SHA
- 79f39a7c
Model card
From the Hugging Face model README
!python llama-recipes/llama_finetuning.py
--use_peft
--num_epochs 1
--peft_method lora
--run_validation false
--quantization
--dataset alpaca_dataset
--model_name meta-llama/Llama-2-7b-chat-hf
--save_model
--save_optimizer
--batch_size_training 8
--output_dir ./save
Training procedure
The following bitsandbytes quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- 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
- Library
- peft
- Type
- llama
- Created
- Aug 15, 2023
- Updated
- Aug 16, 2023