MoLora-v2
Collection
First Prototype of the second iteration of MoLora utilizing mixture of expert techniques applied to the Llama2 model.
•
5 items
•
Updated
•
2
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: float16
Framework versions
- PEFT 0.5.0
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support