Downloads · 30 days
9
31% of all-time downloads
GRATH-gradtruth
weixinchen/GRATH-gradtruth
GRATH-gradtruth is a machine learning model from weixinchen. 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.
This is a gradually self-truthified model (with one iteration) proposed in the paper GRATH: Gradual Self-Truthifying for Large Language Models.
All-time downloads
29
Public
Repo size
25.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin25.2 MB · 91%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jul 17, 2024
- Updated
- Jul 17, 2024
- SHA
- 724b1422
Model card
From the Hugging Face model README
This is a gradually self-truthified model (with one iteration) proposed in the paper GRATH: Gradual Self-Truthifying for Large Language Models.
Note: This model is applied with DPO twice. The reference model of DPO is set as the current base model.
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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
Framework versions
-
PEFT 0.5.0
-
PEFT 0.5.0
- Library
- peft
- Created
- Jul 17, 2024
- Updated
- Jul 17, 2024