Downloads · 30 days
13
7% of all-time downloads
phi-platypus-qlora
openaccess-ai-collective/phi-platypus-qlora
phi-platypus-qlora is a machine learning model from openaccess-ai-collective. 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
179
Public
Parameters
1.4B
3 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors2.8 GB · 96%
At a glance
- Library
- peft
- Model type
- mixformer-sequential
- Access
- Public
- Created
- Sep 12, 2023
- Updated
- Sep 12, 2023
- SHA
- 31c39da9
Datasets
Model card
From the Hugging Face model README
Phi 1.5 Playtpus
QLoRA trained for 2 epochs.
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 0.6.0.dev0
- Library
- peft
- Type
- mixformer-sequential
- Created
- Sep 12, 2023
- Updated
- Sep 12, 2023