BatsResearch
/

Mistral-7B-v0.1-P3

Model card Files Files and versions Community

Edit model card

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: float32

Framework versions

PEFT 0.5.0

Downloads last month: 9

Inference API

Unable to determine this model’s pipeline type. Check the docs .

Collection including BatsResearch/Mistral-7B-v0.1-P3

Bonito

Models and datasets from the Bonito paper (https://arxiv.org/abs/2402.18334) • 8 items • Updated Oct 1 • 1