Downloads · 30 days
11
21% of all-time downloads
EverythingLM-13b-V2-peft
totally-not-an-llm/EverythingLM-13b-V2-peft
EverythingLM-13b-V2-peft is a machine learning model from totally-not-an-llm. 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.
All-time downloads
52
Public
Repo size
6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin4.5 GB · 53%
At a glance
- Library
- peft
- Access
- Public
- Created
- Aug 21, 2023
- Updated
- Aug 22, 2023
- SHA
- e71ad13c
Model card
From the Hugging Face model README
20 epochs on V2 dataset
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- 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: bfloat16
Framework versions
- PEFT 0.5.0.dev0
- Library
- peft
- Created
- Aug 21, 2023
- Updated
- Aug 22, 2023