Trained for 5 epochs on https://huggingface.co./datasets/totally-not-an-llm/EverythingLM-data. Merged model can be found here: https://huggingface.co./totally-not-an-llm/EverythingLM-13b-16k.
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
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for totally-not-an-llm/EverythingLM-13b-peft
Base model
NousResearch/Llama-2-13b-hf