Downloads · 30 days
3
14% of all-time downloads
llama2-peft-lora-violative-checker-v1
fishytorts/llama2-peft-lora-violative-checker-v1
llama2-peft-lora-violative-checker-v1 is a machine learning model from fishytorts. 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.
- GPT4-generated dataset - size: 80 - perdevicetrainbatchsize=4, - gradientaccumulationsteps=4, - warmupsteps=100, - maxsteps=200, - learningrate=2e-4, - fp16=True, - loggingsteps=1, - outputdir='outputs',
All-time downloads
21
Public
Repo size
33.6 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin33.6 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 20, 2023
- Updated
- Sep 20, 2023
- SHA
- 4a401da1
Model card
From the Hugging Face model README
Dataset procedure
- GPT4-generated dataset
- size: 80
- per_device_train_batch_size=4,
- gradient_accumulation_steps=4,
- warmup_steps=100,
- max_steps=200,
- learning_rate=2e-4,
- fp16=True,
- logging_steps=1,
- output_dir='outputs',
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
LoraConfig procedure
r=16, #attention heads
lora_alpha=32, #alpha scaling
# target_modules=["q_proj", "v_proj"], #if you know the
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM" # set this for CLM or Seq2Seq
Framework versions
- PEFT 0.6.0.dev0
- Library
- peft
- Created
- Sep 20, 2023
- Updated
- Sep 20, 2023