Downloads · 30 days
8
5% of all-time downloads
recipe
googcheng/recipe
recipe is a machine learning model from googcheng. 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.
a recipe classify from https://github.com/OpenPipe/OpenPipe lora fine-tune based on llama2-7b, 1hour on 23090
All-time downloads
166
Public
Repo size
372 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin320 MB · 85%
At a glance
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Sep 15, 2023
- Updated
- Sep 20, 2023
- SHA
- 24723947
Base models
Model card
From the Hugging Face model README
title
a recipe classify from https://github.com/OpenPipe/OpenPipe
lora fine-tune based on llama2-7b, 1hour on 2*3090
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- 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 0.6.0.dev0
- Library
- peft
- Type
- llama
- Created
- Sep 15, 2023
- Updated
- Sep 20, 2023