Downloads · 30 days
6
19% of all-time downloads
llama2-TinyPixel-qlora-FT-chinese
yijhen38/llama2-TinyPixel-qlora-FT-chinese
llama2-TinyPixel-qlora-FT-chinese is a machine learning model from yijhen38. 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.
參考 Fine Turning https://colab.research.google.com/drive/12dVqXZMIVxGI0uutU6HG9RWbWPXL3vts?usp=sharingscrollTo=mNnkgBq7Q3EU
All-time downloads
31
Public
Repo size
134 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin134 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jul 28, 2023
- Updated
- Jul 28, 2023
- SHA
- d2326e85
Model card
From the Hugging Face model README
參考 Fine Turning https://colab.research.google.com/drive/12dVqXZMIVxGI0uutU6HG9RWbWPXL3vts?usp=sharing#scrollTo=mNnkgBq7Q3EU
Model：AlexanderDoria/novel17_test dataset：COT_Answer.txt
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: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.5.0.dev0
- Library
- peft
- Created
- Jul 28, 2023
- Updated
- Jul 28, 2023