Hugging Face's logo

kingabzpro
/
zephyr-7b-beta-Agent-Instruct

Text Generation
PEFT
Safetensors
English
pretrained
lora
qlora
4bit
Model card Files Community

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: False
  • bnb_4bit_compute_dtype: bfloat16

Framework versions

  • PEFT 0.7.0
Downloads last month
5
Inference Examples
Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kingabzpro/zephyr-7b-beta-Agent-Instruct

Base model

mistralai/Mistral-7B-v0.1
Finetuned
HuggingFaceH4/zephyr-7b-beta
Adapter
(216)
this model

Dataset used to train kingabzpro/zephyr-7b-beta-Agent-Instruct

Collection including kingabzpro/zephyr-7b-beta-Agent-Instruct